【第26期】(第35屆) ICML2018 Accept-paper List(610篇)

來源：ICML會議

作者：圖靈助手

[1]. Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems.

作者: Marc Abeille,Alessandro Lazaric,

連結: http://proceedings.mlr.press/v80/abeille18a.html

[2]. State Abstractions for Lifelong Reinforcement Learning.

作者: David Abel,Dilip Arumugam,Lucas Lehnert,Michael L. Littman,

連結: http://proceedings.mlr.press/v80/abel18a.html

[3]. Policy and Value Transfer in Lifelong Reinforcement Learning.

作者: David Abel,Yuu Jinnai,Sophie Yue Guo,George Dimitri Konidaris,Michael L. Littman,

連結: http://proceedings.mlr.press/v80/abel18b.html

[4]. INSPECTRE: Privately Estimating the Unseen.

作者: Jayadev Acharya,Gautam Kamath,Ziteng Sun,Huanyu Zhang,

連結: http://proceedings.mlr.press/v80/acharya18a.html

[5]. Learning Representations and Generative Models for 3D Point Clouds.

作者: Panos Achlioptas,Olga Diamanti,Ioannis Mitliagkas,Leonidas J. Guibas,

連結: http://proceedings.mlr.press/v80/achlioptas18a.html

[6]. Discovering Interpretable Representations for Both Deep Generative and Discriminative Models.

作者: Tameem Adel,Zoubin Ghahramani,Adrian Weller,

連結: http://proceedings.mlr.press/v80/adel18a.html

[7]. A Reductions Approach to Fair Classification.

作者: Alekh Agarwal,Alina Beygelzimer,Miroslav Dudík,John Langford,Hanna M. Wallach,

連結: http://proceedings.mlr.press/v80/agarwal18a.html

[8]. Accelerated Spectral Ranking.

作者: Arpit Agarwal,Prathamesh Patil,Shivani Agarwal,

連結: http://proceedings.mlr.press/v80/agarwal18b.html

[9]. MISSION: Ultra Large-Scale Feature Selection using Count-Sketches.

作者: Amirali Aghazadeh,Ryan Spring,Daniel LeJeune,Gautam Dasarathy,Anshumali Shrivastava,Richard G. Baraniuk,

連結: http://proceedings.mlr.press/v80/aghazadeh18a.html

[10]. Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models.

作者: Raj Agrawal,Caroline Uhler,Tamara Broderick,

連結: http://proceedings.mlr.press/v80/agrawal18a.html

[11]. Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy.

作者: Shipra Agrawal,Morteza Zadimoghaddam,Vahab S. Mirrokni,

連結: http://proceedings.mlr.press/v80/agrawal18b.html

[12]. Bucket Renormalization for Approximate Inference.

作者: Sungsoo Ahn,Michael Chertkov,Adrian Weller,Jinwoo Shin,

連結: http://proceedings.mlr.press/v80/ahn18a.html

[13]. oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis.

作者: Samuel K. Ainsworth,Nicholas J. Foti,Adrian K. C. Lee,Emily B. Fox,

連結: http://proceedings.mlr.press/v80/ainsworth18a.html

[14]. Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design.

作者: Ahmed M. Alaa,Mihaela van der Schaar,

連結: http://proceedings.mlr.press/v80/alaa18a.html

[15]. AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning.

作者: Ahmed M. Alaa,Mihaela van der Schaar,

連結: http://proceedings.mlr.press/v80/alaa18b.html

[16]. Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization.

作者: Ibrahim M. Alabdulmohsin,

連結: http://proceedings.mlr.press/v80/alabdulmohsin18a.html

[17]. Fixing a Broken ELBO.

作者: Alexander A. Alemi,Ben Poole,Ian Fischer,Joshua V. Dillon,Rif A. Saurous,Kevin Murphy,

連結: http://proceedings.mlr.press/v80/alemi18a.html

[18]. Differentially Private Identity and Equivalence Testing of Discrete Distributions.

作者: Maryam Aliakbarpour,Ilias Diakonikolas,Ronitt Rubinfeld,

連結: http://proceedings.mlr.press/v80/aliakbarpour18a.html

[19]. Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization.

作者: Zeyuan Allen-Zhu,

連結: http://proceedings.mlr.press/v80/allen-zhu18a.html

[20]. Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits.

作者: Zeyuan Allen-Zhu,Sébastien Bubeck,Yuanzhi Li,

連結: http://proceedings.mlr.press/v80/allen-zhu18b.html

[21]. Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data.

作者: Amjad Almahairi,Sai Rajeswar,Alessandro Sordoni,Philip Bachman,Aaron C. Courville,

連結: http://proceedings.mlr.press/v80/almahairi18a.html

[22]. Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory.

作者: Ron Amit,Ron Meir,

連結: http://proceedings.mlr.press/v80/amit18a.html

[23]. MAGAN: Aligning Biological Manifolds.

作者: Matthew Amodio,Smita Krishnaswamy,

連結: http://proceedings.mlr.press/v80/amodio18a.html

[24]. Subspace Embedding and Linear Regression with Orlicz Norm.

作者: Alexandr Andoni,Chengyu Lin,Ying Sheng,Peilin Zhong,Ruiqi Zhong,

連結: http://proceedings.mlr.press/v80/andoni18a.html

[25]. Efficient Gradient-Free Variational Inference using Policy Search.

作者: Oleg Arenz,Mingjun Zhong,Gerhard Neumann,

連結: http://proceedings.mlr.press/v80/arenz18a.html

[26]. On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization.

作者: Sanjeev Arora,Nadav Cohen,Elad Hazan,

連結: http://proceedings.mlr.press/v80/arora18a.html

[27]. Stronger Generalization Bounds for Deep Nets via a Compression Approach.

作者: Sanjeev Arora,Rong Ge,Behnam Neyshabur,Yi Zhang,

連結: http://proceedings.mlr.press/v80/arora18b.html

[28]. Lipschitz Continuity in Model-based Reinforcement Learning.

作者: Kavosh Asadi,Dipendra Misra,Michael L. Littman,

連結: http://proceedings.mlr.press/v80/asadi18a.html

[29]. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples.

作者: Anish Athalye,Nicholas Carlini,David A. Wagner,

連結: http://proceedings.mlr.press/v80/athalye18a.html

[30]. Synthesizing Robust Adversarial Examples.

作者: Anish Athalye,Logan Engstrom,Andrew Ilyas,Kevin Kwok,

連結: http://proceedings.mlr.press/v80/athalye18b.html

[31]. Clustering Semi-Random Mixtures of Gaussians.

作者: Pranjal Awasthi,Aravindan Vijayaraghavan,

連結: http://proceedings.mlr.press/v80/awasthi18a.html

[32]. Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing.

作者: Davide Bacciu,Federico Errica,Alessio Micheli,

連結: http://proceedings.mlr.press/v80/bacciu18a.html

[33]. Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions.

作者: Wenruo Bai,Jeffrey A. Bilmes,

連結: http://proceedings.mlr.press/v80/bai18a.html

[34]. Comparing Dynamics: Deep Neural Networks versus Glassy Systems.

作者: Marco Baity-Jesi,Levent Sagun,Mario Geiger,Stefano Spigler,Gérard Ben Arous,Chiara Cammarota,Yann LeCun,Matthieu Wyart,Giulio Biroli,

連結: http://proceedings.mlr.press/v80/baity-jesi18a.html

[35]. SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions.

作者: Chandrajit Bajaj,Tingran Gao,Zihang He,Qixing Huang,Zhenxiao Liang,

連結: http://proceedings.mlr.press/v80/bajaj18a.html

[36]. A Boo(n) for Evaluating Architecture Performance.

作者: Ondrej Bajgar,Rudolf Kadlec,Jan Kleindienst,

連結: http://proceedings.mlr.press/v80/bajgar18a.html

[37]. Learning to Branch.

作者: Maria-Florina Balcan,Travis Dick,Tuomas Sandholm,Ellen Vitercik,

連結: http://proceedings.mlr.press/v80/balcan18a.html

[38]. The Mechanics of n-Player Differentiable Games.

作者: David Balduzzi,Sébastien Racanière,James Martens,Jakob N. Foerster,Karl Tuyls,Thore Graepel,

連結: http://proceedings.mlr.press/v80/balduzzi18a.html

[39]. Spline Filters For End-to-End Deep Learning.

作者: Randall Balestriero,Romain Cosentino,Hervé Glotin,Richard G. Baraniuk,

連結: http://proceedings.mlr.press/v80/balestriero18a.html

[40]. A Spline Theory of Deep Networks.

作者: Randall Balestriero,Richard G. Baraniuk,

連結: http://proceedings.mlr.press/v80/balestriero18b.html

[41]. Approximation Guarantees for Adaptive Sampling.

作者: Eric Balkanski,Yaron Singer,

連結: http://proceedings.mlr.press/v80/balkanski18a.html

[42]. Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising.

作者: Borja Balle,Yu-Xiang Wang,

連結: http://proceedings.mlr.press/v80/balle18a.html

[43]. Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients.

作者: Lukas Balles,Philipp Hennig,

連結: http://proceedings.mlr.press/v80/balles18a.html

[44]. Differentially Private Database Release via Kernel Mean Embeddings.

作者: Matej Balog,Ilya O. Tolstikhin,Bernhard Schölkopf,

連結: http://proceedings.mlr.press/v80/balog18a.html

[45]. Improving Optimization in Models With Continuous Symmetry Breaking.

作者: Robert Bamler,Stephan Mandt,

連結: http://proceedings.mlr.press/v80/bamler18a.html

[46]. Improved Training of Generative Adversarial Networks using Representative Features.

作者: Duhyeon Bang,Hyunjung Shim,

連結: http://proceedings.mlr.press/v80/bang18a.html

[47]. Using Inherent Structures to design Lean 2-layer RBMs.

作者: Abhishek Bansal,Abhinav Anand,Chiranjib Bhattacharyya,

連結: http://proceedings.mlr.press/v80/bansal18a.html

[48]. Classification from Pairwise Similarity and Unlabeled Data.

作者: Han Bao,Gang Niu,Masashi Sugiyama,

連結: http://proceedings.mlr.press/v80/bao18a.html

[49]. Bayesian Optimization of Combinatorial Structures.

作者: Ricardo Baptista,Matthias Poloczek,

連結: http://proceedings.mlr.press/v80/baptista18a.html

[50]. Geodesic Convolutional Shape Optimization.

作者: Pierre Baqué,Edoardo Remelli,François Fleuret,Pascal Fua,

連結: http://proceedings.mlr.press/v80/baque18a.html

[51]. Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems.

作者: Eugenio Bargiacchi,Timothy Verstraeten,Diederik M. Roijers,Ann Nowé,Hado van Hasselt,

連結: http://proceedings.mlr.press/v80/bargiacchi18a.html

[52]. Testing Sparsity over Known and Unknown Bases.

作者: Siddharth Barman,Arnab Bhattacharyya,Suprovat Ghoshal,

連結: http://proceedings.mlr.press/v80/barman18a.html

[53]. Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement.

作者: André Barreto,Diana Borsa,John Quan,Tom Schaul,David Silver,Matteo Hessel,Daniel J. Mankowitz,Augustin Zídek,Rémi Munos,

連結: http://proceedings.mlr.press/v80/barreto18a.html

[54]. Gradient descent with identity initialization efficiently learns positive definite linear transformations.

作者: Peter L. Bartlett,David P. Helmbold,Philip M. Long,

連結: http://proceedings.mlr.press/v80/bartlett18a.html

[55]. Mutual Information Neural Estimation.

作者: Mohamed Ishmael Belghazi,Aristide Baratin,Sai Rajeswar,Sherjil Ozair,Yoshua Bengio,R. Devon Hjelm,Aaron C. Courville,

連結: http://proceedings.mlr.press/v80/belghazi18a.html

[56]. To Understand Deep Learning We Need to Understand Kernel Learning.

作者: Mikhail Belkin,Siyuan Ma,Soumik Mandal,

連結: http://proceedings.mlr.press/v80/belkin18a.html

[57]. Understanding and Simplifying One-Shot Architecture Search.

作者: Gabriel Bender,Pieter-Jan Kindermans,Barret Zoph,Vijay Vasudevan,Quoc V. Le,

連結: http://proceedings.mlr.press/v80/bender18a.html

[58]. SIGNSGD: Compressed Optimisation for Non-Convex Problems.

作者: Jeremy Bernstein,Yu-Xiang Wang,Kamyar Azizzadenesheli,Animashree Anandkumar,

連結: http://proceedings.mlr.press/v80/bernstein18a.html

[59]. Distributed Clustering via LSH Based Data Partitioning.

作者: Aditya Bhaskara,Maheshakya Wijewardena,

連結: http://proceedings.mlr.press/v80/bhaskara18a.html

[60]. Autoregressive Convolutional Neural Networks for Asynchronous Time Series.

作者: Mikolaj Binkowski,Gautier Marti,Philippe Donnat,

連結: http://proceedings.mlr.press/v80/binkowski18a.html

[61]. Adaptive Sampled Softmax with Kernel Based Sampling.

作者: Guy Blanc,Steffen Rendle,

連結: http://proceedings.mlr.press/v80/blanc18a.html

[62]. Optimizing the Latent Space of Generative Networks.

作者: Piotr Bojanowski,Armand Joulin,David Lopez-Paz,Arthur Szlam,

連結: http://proceedings.mlr.press/v80/bojanowski18a.html

[63]. NetGAN: Generating Graphs via Random Walks.

作者: Aleksandar Bojchevski,Oleksandr Shchur,Daniel Zügner,Stephan Günnemann,

連結: http://proceedings.mlr.press/v80/bojchevski18a.html

[64]. A Progressive Batching L-BFGS Method for Machine Learning.

作者: Raghu Bollapragada,Dheevatsa Mudigere,Jorge Nocedal,Hao-Jun Michael Shi,Ping Tak Peter Tang,

連結: http://proceedings.mlr.press/v80/bollapragada18a.html

[65]. Prediction Rule Reshaping.

作者: Matt Bonakdarpour,Sabyasachi Chatterjee,Rina Foygel Barber,John Lafferty,

連結: http://proceedings.mlr.press/v80/bonakdarpour18a.html

[66]. QuantTree: Histograms for Change Detection in Multivariate Data Streams.

作者: Giacomo Boracchi,Diego Carrera,Cristiano Cervellera,Danilo Macciò,

連結: http://proceedings.mlr.press/v80/boracchi18a.html

[67]. Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order.

作者: Vladimir Braverman,Stephen R. Chestnut,Robert Krauthgamer,Yi Li,David P. Woodruff,Lin F. Yang,

連結: http://proceedings.mlr.press/v80/braverman18a.html

[68]. Predict and Constrain: Modeling Cardinality in Deep Structured Prediction.

作者: Nataly Brukhim,Amir Globerson,

連結: http://proceedings.mlr.press/v80/brukhim18a.html

[69]. Quasi-Monte Carlo Variational Inference.

作者: Alexander Buchholz,Florian Wenzel,Stephan Mandt,

連結: http://proceedings.mlr.press/v80/buchholz18a.html

[70]. Path-Level Network Transformation for Efficient Architecture Search.

作者: Han Cai,Jiacheng Yang,Weinan Zhang,Song Han,Yong Yu,

連結: http://proceedings.mlr.press/v80/cai18a.html

[71]. Improved Large-Scale Graph Learning through Ridge Spectral Sparsification.

作者: Daniele Calandriello,Ioannis Koutis,Alessandro Lazaric,Michal Valko,

連結: http://proceedings.mlr.press/v80/calandriello18a.html

[72]. Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent.

作者: Trevor Campbell,Tamara Broderick,

連結: http://proceedings.mlr.press/v80/campbell18a.html

[73]. Adversarial Learning with Local Coordinate Coding.

作者: Jiezhang Cao,Yong Guo,Qingyao Wu,Chunhua Shen,Junzhou Huang,Mingkui Tan,

連結: http://proceedings.mlr.press/v80/cao18a.html

[74]. Fair and Diverse DPP-Based Data Summarization.

作者: L. Elisa Celis,Vijay Keswani,Damian Straszak,Amit Deshpande,Tarun Kathuria,Nisheeth K. Vishnoi,

連結: http://proceedings.mlr.press/v80/celis18a.html

[75]. Conditional Noise-Contrastive Estimation of Unnormalised Models.

作者: Ciwan Ceylan,Michael U. Gutmann,

連結: http://proceedings.mlr.press/v80/ceylan18a.html

[76]. Adversarial Time-to-Event Modeling.

作者: Paidamoyo Chapfuwa,Chenyang Tao,Chunyuan Li,Courtney Page,Benjamin Goldstein,Lawrence Carin,Ricardo Henao,

連結: http://proceedings.mlr.press/v80/chapfuwa18a.html

[77]. Stability and Generalization of Learning Algorithms that Converge to Global Optima.

作者: Zachary B. Charles,Dimitris S. Papailiopoulos,

連結: http://proceedings.mlr.press/v80/charles18a.html

[78]. Learning and Memorization.

作者: Satrajit Chatterjee,

連結: http://proceedings.mlr.press/v80/chatterjee18a.html

[79]. On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo.

作者: Niladri S. Chatterji,Nicolas Flammarion,Yi-An Ma,Peter L. Bartlett,Michael I. Jordan,

連結: http://proceedings.mlr.press/v80/chatterji18a.html

[80]. Hierarchical Clustering with Structural Constraints.

作者: Vaggos Chatziafratis,Rad Niazadeh,Moses Charikar,

連結: http://proceedings.mlr.press/v80/chatziafratis18a.html

[81]. Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series.

作者: Zhengping Che,Sanjay Purushotham,Max Guangyu Li,Bo Jiang,Yan Liu,

連結: http://proceedings.mlr.press/v80/che18a.html

[82]. GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks.

作者: Zhao Chen,Vijay Badrinarayanan,Chen-Yu Lee,Andrew Rabinovich,

連結: http://proceedings.mlr.press/v80/chen18a.html

[83]. Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?

作者: Lin Chen,Moran Feldman,Amin Karbasi,

連結: http://proceedings.mlr.press/v80/chen18b.html

[84]. Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity.

作者: Lin Chen,Christopher Harshaw,Hamed Hassani,Amin Karbasi,

連結: http://proceedings.mlr.press/v80/chen18c.html

[85]. Continuous-Time Flows for Efficient Inference and Density Estimation.

作者: Changyou Chen,Chunyuan Li,Liquan Chen,Wenlin Wang,Yunchen Pu,Lawrence Carin,

連結: http://proceedings.mlr.press/v80/chen18d.html

[86]. Scalable Bilinear Learning Using State and Action Features.

作者: Yichen Chen,Lihong Li,Mengdi Wang,

連結: http://proceedings.mlr.press/v80/chen18e.html

[87]. Stein Points.

作者: Wilson Ye Chen,Lester W. Mackey,Jackson Gorham,François-Xavier Briol,Chris J. Oates,

連結: http://proceedings.mlr.press/v80/chen18f.html

[88]. Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations.

作者: Ting Chen,Martin Renqiang Min,Yizhou Sun,

連結: http://proceedings.mlr.press/v80/chen18g.html

[89]. PixelSNAIL: An Improved Autoregressive Generative Model.

作者: Xi Chen,Nikhil Mishra,Mostafa Rohaninejad,Pieter Abbeel,

連結: http://proceedings.mlr.press/v80/chen18h.html

[90]. Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks.

作者: Minmin Chen,Jeffrey Pennington,Samuel S. Schoenholz,

連結: http://proceedings.mlr.press/v80/chen18i.html

[91]. Learning to Explain: An Information-Theoretic Perspective on Model Interpretation.

作者: Jianbo Chen,Le Song,Martin J. Wainwright,Michael I. Jordan,

連結: http://proceedings.mlr.press/v80/chen18j.html

[92]. Variational Inference and Model Selection with Generalized Evidence Bounds.

作者: Liqun Chen,Chenyang Tao,Ruiyi Zhang,Ricardo Henao,Lawrence Carin,

連結: http://proceedings.mlr.press/v80/chen18k.html

[93]. DRACO: Byzantine-resilient Distributed Training via Redundant Gradients.

作者: Lingjiao Chen,Hongyi Wang,Zachary B. Charles,Dimitris S. Papailiopoulos,

連結: http://proceedings.mlr.press/v80/chen18l.html

[94]. SADAGRAD: Strongly Adaptive Stochastic Gradient Methods.

作者: Zaiyi Chen,Yi Xu,Enhong Chen,Tianbao Yang,

連結: http://proceedings.mlr.press/v80/chen18m.html

[95]. Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization.

作者: Jinghui Chen,Pan Xu,Lingxiao Wang,Jian Ma,Quanquan Gu,

連結: http://proceedings.mlr.press/v80/chen18n.html

[96]. End-to-End Learning for the Deep Multivariate Probit Model.

作者: Di Chen,Yexiang Xue,Carla P. Gomes,

連結: http://proceedings.mlr.press/v80/chen18o.html

[97]. Stochastic Training of Graph Convolutional Networks with Variance Reduction.

作者: Jianfei Chen,Jun Zhu,Le Song,

連結: http://proceedings.mlr.press/v80/chen18p.html

[98]. Extreme Learning to Rank via Low Rank Assumption.

作者: Minhao Cheng,Ian Davidson,Cho-Jui Hsieh,

連結: http://proceedings.mlr.press/v80/cheng18a.html

[99]. Learning a Mixture of Two Multinomial Logits.

作者: Flavio Chierichetti,Ravi Kumar,Andrew Tomkins,

連結: http://proceedings.mlr.press/v80/chierichetti18a.html

[100]. Structured Evolution with Compact Architectures for Scalable Policy Optimization.

作者: Krzysztof Choromanski,Mark Rowland,Vikas Sindhwani,Richard E. Turner,Adrian Weller,

連結: http://proceedings.mlr.press/v80/choromanski18a.html

[101]. Path Consistency Learning in Tsallis Entropy Regularized MDPs.

作者: Yinlam Chow,Ofir Nachum,Mohammad Ghavamzadeh,

連結: http://proceedings.mlr.press/v80/chow18a.html

[102]. An Iterative, Sketching-based Framework for Ridge Regression.

作者: Agniva Chowdhury,Jiasen Yang,Petros Drineas,

連結: http://proceedings.mlr.press/v80/chowdhury18a.html

[103]. Stochastic Wasserstein Barycenters.

作者: Sebastian Claici,Edward Chien,Justin Solomon,

連結: http://proceedings.mlr.press/v80/claici18a.html

[104]. Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings.

作者: John D. Co-Reyes,Yuxuan Liu,Abhishek Gupta,Benjamin Eysenbach,Pieter Abbeel,Sergey Levine,

連結: http://proceedings.mlr.press/v80/co-reyes18a.html

[105]. On Acceleration with Noise-Corrupted Gradients.

作者: Michael Cohen,Jelena Diakonikolas,Lorenzo Orecchia,

連結: http://proceedings.mlr.press/v80/cohen18a.html

[106]. Online Linear Quadratic Control.

作者: Alon Cohen,Avinatan Hassidim,Tomer Koren,Nevena Lazic,Yishay Mansour,Kunal Talwar,

連結: http://proceedings.mlr.press/v80/cohen18b.html

[107]. GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms.

作者: Cédric Colas,Olivier Sigaud,Pierre-Yves Oudeyer,

連結: http://proceedings.mlr.press/v80/colas18a.html

[108]. Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski p-Norms.

作者: Graham Cormode,Charlie Dickens,David P. Woodruff,

連結: http://proceedings.mlr.press/v80/cormode18a.html

[109]. Efficient ModelBased Deep Reinforcement Learning with Variational State Tabulation.

作者: Dane S. Corneil,Wulfram Gerstner,Johanni Brea,

連結: http://proceedings.mlr.press/v80/corneil18a.html

[110]. Online Learning with Abstention.

作者: Corinna Cortes,Giulia DeSalvo,Claudio Gentile,Mehryar Mohri,Scott Yang,

連結: http://proceedings.mlr.press/v80/cortes18a.html

[111]. Constrained Interacting Submodular Groupings.

作者: Andrew Cotter,Mahdi Milani Fard,Seungil You,Maya R. Gupta,Jeff A. Bilmes,

連結: http://proceedings.mlr.press/v80/cotter18a.html

[112]. Inference Suboptimality in Variational Autoencoders.

作者: Chris Cremer,Xuechen Li,David Duvenaud,

連結: http://proceedings.mlr.press/v80/cremer18a.html

[113]. Mix & Match Agent Curricula for Reinforcement Learning.

作者: Wojciech Marian Czarnecki,Siddhant M. Jayakumar,Max Jaderberg,Leonard Hasenclever,Yee Whye Teh,Nicolas Heess,Simon Osindero,Razvan Pascanu,

連結: http://proceedings.mlr.press/v80/czarnecki18a.html

[114]. Implicit Quantile Networks for Distributional Reinforcement Learning.

作者: Will Dabney,Georg Ostrovski,David Silver,Rémi Munos,

連結: http://proceedings.mlr.press/v80/dabney18a.html

[115]. Learning Steady-States of Iterative Algorithms over Graphs.

作者: Hanjun Dai,Zornitsa Kozareva,Bo Dai,Alexander J. Smola,Le Song,

連結: http://proceedings.mlr.press/v80/dai18a.html

[116]. Adversarial Attack on Graph Structured Data.

作者: Hanjun Dai,Hui Li,Tian Tian,Xin Huang,Lin Wang,Jun Zhu,Le Song,

連結: http://proceedings.mlr.press/v80/dai18b.html

[117]. SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation.

作者: Bo Dai,Albert Shaw,Lihong Li,Lin Xiao,Niao He,Zhen Liu,Jianshu Chen,Le Song,

連結: http://proceedings.mlr.press/v80/dai18c.html

[118]. Compressing Neural Networks using the Variational Information Bottleneck.

作者: Bin Dai,Chen Zhu,Baining Guo,David P. Wipf,

連結: http://proceedings.mlr.press/v80/dai18d.html

[119]. Asynchronous Byzantine Machine Learning (the case of SGD).

作者: Georgios Damaskinos,El Mahdi El Mhamdi,Rachid Guerraoui,Rhicheek Patra,Mahsa Taziki,

連結: http://proceedings.mlr.press/v80/damaskinos18a.html

[120]. Escaping Saddles with Stochastic Gradients.

作者: Hadi Daneshmand,Jonas Moritz Kohler,Aurélien Lucchi,Thomas Hofmann,

連結: http://proceedings.mlr.press/v80/daneshmand18a.html

[121]. Minibatch Gibbs Sampling on Large Graphical Models.

作者: Christopher De Sa,Vincent Chen,Wing Wong,

連結: http://proceedings.mlr.press/v80/de-sa18a.html

[122]. Stochastic Video Generation with a Learned Prior.

作者: Emily Denton,Rob Fergus,

連結: http://proceedings.mlr.press/v80/denton18a.html

[123]. Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning.

作者: Stefan Depeweg,José Miguel Hernández-Lobato,Finale Doshi-Velez,Steffen Udluft,

連結: http://proceedings.mlr.press/v80/depeweg18a.html

[124]. Accurate Inference for Adaptive Linear Models.

作者: Yash Deshpande,Lester W. Mackey,Vasilis Syrgkanis,Matt Taddy,

連結: http://proceedings.mlr.press/v80/deshpande18a.html

[125]. Variational Network Inference: Strong and Stable with Concrete Support.

作者: Amir Dezfouli,Edwin V. Bonilla,Richard Nock,

連結: http://proceedings.mlr.press/v80/dezfouli18a.html

[126]. Modeling Sparse Deviations for Compressed Sensing using Generative Models.

作者: Manik Dhar,Aditya Grover,Stefano Ermon,

連結: http://proceedings.mlr.press/v80/dhar18a.html

[127]. Alternating Randomized Block Coordinate Descent.

作者: Jelena Diakonikolas,Lorenzo Orecchia,

連結: http://proceedings.mlr.press/v80/diakonikolas18a.html

[128]. Learning to Act in Decentralized Partially Observable MDPs.

作者: Jilles Steeve Dibangoye,Olivier Buffet,

連結: http://proceedings.mlr.press/v80/dibangoye18a.html

[129]. Noisin: Unbiased Regularization for Recurrent Neural Networks.

作者: Adji Bousso Dieng,Rajesh Ranganath,Jaan Altosaar,David M. Blei,

連結: http://proceedings.mlr.press/v80/dieng18a.html

[130]. Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning.

作者: Thomas G. Dietterich,George Trimponias,Zhitang Chen,

連結: http://proceedings.mlr.press/v80/dietterich18a.html

[131]. Coordinated Exploration in Concurrent Reinforcement Learning.

作者: Maria Dimakopoulou,Benjamin Van Roy,

連結: http://proceedings.mlr.press/v80/dimakopoulou18a.html

[132]. Probabilistic Recurrent State-Space Models.

作者: Andreas Doerr,Christian Daniel,Martin Schiegg,Duy Nguyen-Tuong,Stefan Schaal,Marc Toussaint,Sebastian Trimpe,

連結: http://proceedings.mlr.press/v80/doerr18a.html

[133]. Randomized Block Cubic Newton Method.

作者: Nikita Doikov,Peter Richtárik,

連結: http://proceedings.mlr.press/v80/doikov18a.html

[134]. Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering.

作者: Ahmed Douik,Babak Hassibi,

連結: http://proceedings.mlr.press/v80/douik18a.html

[135]. Essentially No Barriers in Neural Network Energy Landscape.

作者: Felix Draxler,Kambis Veschgini,Manfred Salmhofer,Fred A. Hamprecht,

連結: http://proceedings.mlr.press/v80/draxler18a.html

[136]. Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer.

作者: Alexey Drutsa,

連結: http://proceedings.mlr.press/v80/drutsa18a.html

[137]. On the Power of Over-parametrization in Neural Networks with Quadratic Activation.

作者: Simon S. Du,Jason D. Lee,

連結: http://proceedings.mlr.press/v80/du18a.html

[138]. Investigating Human Priors for Playing Video Games.

作者: Rachit Dubey,Pulkit Agrawal,Deepak Pathak,Tom Griffiths,Alexei A. Efros,

連結: http://proceedings.mlr.press/v80/dubey18a.html

[139]. A Distributed Second-Order Algorithm You Can Trust.

作者: Celestine Dünner,Aurélien Lucchi,Matilde Gargiani,An Bian,Thomas Hofmann,Martin Jaggi,

連結: http://proceedings.mlr.press/v80/duenner18a.html

[140]. Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors.

作者: Gintare Karolina Dziugaite,Daniel M. Roy,

連結: http://proceedings.mlr.press/v80/dziugaite18a.html

[141]. Beyond the One-Step Greedy Approach in Reinforcement Learning.

作者: Yonathan Efroni,Gal Dalal,Bruno Scherrer,Shie Mannor,

連結: http://proceedings.mlr.press/v80/efroni18a.html

[142]. Parallel and Streaming Algorithms for K-Core Decomposition.

作者: Hossein Esfandiari,Silvio Lattanzi,Vahab S. Mirrokni,

連結: http://proceedings.mlr.press/v80/esfandiari18a.html

[143]. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

作者: Lasse Espeholt,Hubert Soyer,Rémi Munos,Karen Simonyan,Volodymyr Mnih,Tom Ward,Yotam Doron,Vlad Firoiu,Tim Harley,Iain Dunning,Shane Legg,Koray Kavukcuoglu,

連結: http://proceedings.mlr.press/v80/espeholt18a.html

[144]. Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF).

作者: Trefor W. Evans,Prasanth B. Nair,

連結: http://proceedings.mlr.press/v80/evans18a.html

[145]. The Limits of Maxing, Ranking, and Preference Learning.

作者: Moein Falahatgar,Ayush Jain,Alon Orlitsky,Venkatadheeraj Pichapati,Vaishakh Ravindrakumar,

連結: http://proceedings.mlr.press/v80/falahatgar18a.html

[146]. BOHB: Robust and Efficient Hyperparameter Optimization at Scale.

作者: Stefan Falkner,Aaron Klein,Frank Hutter,

連結: http://proceedings.mlr.press/v80/falkner18a.html

[147]. More Robust Doubly Robust Off-policy Evaluation.

作者: Mehrdad Farajtabar,Yinlam Chow,Mohammad Ghavamzadeh,

連結: http://proceedings.mlr.press/v80/farajtabar18a.html

[148]. Efficient and Consistent Adversarial Bipartite Matching.

作者: Rizal Fathony,Sima Behpour,Xinhua Zhang,Brian D. Ziebart,

連結: http://proceedings.mlr.press/v80/fathony18a.html

[149]. Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.

作者: Maryam Fazel,Rong Ge,Sham M. Kakade,Mehran Mesbahi,

連結: http://proceedings.mlr.press/v80/fazel18a.html

[150]. CRVI: Convex Relaxation for Variational Inference.

作者: Ghazal Fazelnia,John W. Paisley,

連結: http://proceedings.mlr.press/v80/fazelnia18a.html

[151]. Fourier Policy Gradients.

作者: Matthew Fellows,Kamil Ciosek,Shimon Whiteson,

連結: http://proceedings.mlr.press/v80/fellows18a.html

[152]. Nonparametric variable importance using an augmented neural network with multi-task learning.

作者: Jean Feng,Brian D. Williamson,Marco Carone,Noah Simon,

連結: http://proceedings.mlr.press/v80/feng18a.html

[153]. Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization.

作者: Louis Filstroff,Alberto Lumbreras,Cédric Févotte,

連結: http://proceedings.mlr.press/v80/filstroff18a.html

[154]. Automatic Goal Generation for Reinforcement Learning Agents.

作者: Carlos Florensa,David Held,Xinyang Geng,Pieter Abbeel,

連結: http://proceedings.mlr.press/v80/florensa18a.html

[155]. DiCE: The Infinitely Differentiable Monte Carlo Estimator.

作者: Jakob N. Foerster,Gregory Farquhar,Maruan Al-Shedivat,Tim Rocktäschel,Eric P. Xing,Shimon Whiteson,

連結: http://proceedings.mlr.press/v80/foerster18a.html

[156]. Practical Contextual Bandits with Regression Oracles.

作者: Dylan J. Foster,Alekh Agarwal,Miroslav Dudík,Haipeng Luo,Robert E. Schapire,

連結: http://proceedings.mlr.press/v80/foster18a.html

[157]. Generative Temporal Models with Spatial Memory for Partially Observed Environments.

作者: Marco Fraccaro,Danilo Jimenez Rezende,Yori Zwols,Alexander Pritzel,S. M. Ali Eslami,Fabio Viola,

連結: http://proceedings.mlr.press/v80/fraccaro18a.html

[158]. ADMM and Accelerated ADMM as Continuous Dynamical Systems.

作者: Guilherme França,Daniel P. Robinson,René Vidal,

連結: http://proceedings.mlr.press/v80/franca18a.html

[159]. Bilevel Programming for Hyperparameter Optimization and Meta-Learning.

作者: Luca Franceschi,Paolo Frasconi,Saverio Salzo,Riccardo Grazzi,Massimiliano Pontil,

連結: http://proceedings.mlr.press/v80/franceschi18a.html

[160]. Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning.

作者: Ronan Fruit,Matteo Pirotta,Alessandro Lazaric,Ronald Ortner,

連結: http://proceedings.mlr.press/v80/fruit18a.html

[161]. Addressing Function Approximation Error in Actor-Critic Methods.

作者: Scott Fujimoto,Herke van Hoof,David Meger,

連結: http://proceedings.mlr.press/v80/fujimoto18a.html

[162]. Clipped Action Policy Gradient.

作者: Yasuhiro Fujita,Shin-ichi Maeda,

連結: http://proceedings.mlr.press/v80/fujita18a.html

[163]. Born-Again Neural Networks.

作者: Tommaso Furlanello,Zachary Chase Lipton,Michael Tschannen,Laurent Itti,Anima Anandkumar,

連結: http://proceedings.mlr.press/v80/furlanello18a.html

[164]. Local Private Hypothesis Testing: Chi-Square Tests.

作者: Marco Gaboardi,Ryan Rogers,

連結: http://proceedings.mlr.press/v80/gaboardi18a.html

[165]. Inductive Two-layer Modeling with Parametric Bregman Transfer.

作者: Vignesh Ganapathiraman,Zhan Shi,Xinhua Zhang,Yaoliang Yu,

連結: http://proceedings.mlr.press/v80/ganapathiraman18a.html

[166]. Hyperbolic Entailment Cones for Learning Hierarchical Embeddings.

作者: Octavian-Eugen Ganea,Gary Bécigneul,Thomas Hofmann,

連結: http://proceedings.mlr.press/v80/ganea18a.html

[167]. Parameterized Algorithms for the Matrix Completion Problem.

作者: Robert Ganian,Iyad A. Kanj,Sebastian Ordyniak,Stefan Szeider,

連結: http://proceedings.mlr.press/v80/ganian18a.html

[168]. Synthesizing Programs for Images using Reinforced Adversarial Learning.

作者: Yaroslav Ganin,Tejas Kulkarni,Igor Babuschkin,S. M. Ali Eslami,Oriol Vinyals,

連結: http://proceedings.mlr.press/v80/ganin18a.html

[169]. Spotlight: Optimizing Device Placement for Training Deep Neural Networks.

作者: Yuanxiang Gao,Li Chen,Baochun Li,

連結: http://proceedings.mlr.press/v80/gao18a.html

[170]. Parallel Bayesian Network Structure Learning.

作者: Tian Gao,Dennis Wei,

連結: http://proceedings.mlr.press/v80/gao18b.html

[171]. Conditional Neural Processes.

作者: Marta Garnelo,Dan Rosenbaum,Christopher Maddison,Tiago Ramalho,David Saxton,Murray Shanahan,Yee Whye Teh,Danilo Jimenez Rezende,S. M. Ali Eslami,

連結: http://proceedings.mlr.press/v80/garnelo18a.html

[172]. Temporal Poisson Square Root Graphical Models.

作者: Sinong Geng,Zhaobin Kuang,Peggy L. Peissig,David Page,

連結: http://proceedings.mlr.press/v80/geng18a.html

[173]. The Generalization Error of Dictionary Learning with Moreau Envelopes.

作者: Alexandros Georgogiannis,

連結: http://proceedings.mlr.press/v80/georgogiannis18a.html

[174]. Budgeted Experiment Design for Causal Structure Learning.

作者: AmirEmad Ghassami,Saber Salehkaleybar,Negar Kiyavash,Elias Bareinboim,

連結: http://proceedings.mlr.press/v80/ghassami18a.html

[175]. Linear Spectral Estimators and an Application to Phase Retrieval.

作者: Ramina Ghods,Andrew S. Lan,Tom Goldstein,Christoph Studer,

連結: http://proceedings.mlr.press/v80/ghods18a.html

[176]. Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors.

作者: Soumya Ghosh,Jiayu Yao,Finale Doshi-Velez,

連結: http://proceedings.mlr.press/v80/ghosh18a.html

[177]. Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time.

作者: Asish Ghoshal,Jean Honorio,

連結: http://proceedings.mlr.press/v80/ghoshal18a.html

[178]. Robust and Scalable Models of Microbiome Dynamics.

作者: Travis E. Gibson,Georg K. Gerber,

連結: http://proceedings.mlr.press/v80/gibson18a.html

[179]. Non-Linear Motor Control by Local Learning in Spiking Neural Networks.

作者: Aditya Gilra,Wulfram Gerstner,

連結: http://proceedings.mlr.press/v80/gilra18a.html

[180]. Learning One Convolutional Layer with Overlapping Patches.

作者: Surbhi Goel,Adam R. Klivans,Raghu Meka,

連結: http://proceedings.mlr.press/v80/goel18a.html

[181]. Visualizing and Understanding Atari Agents.

作者: Samuel Greydanus,Anurag Koul,Jonathan Dodge,Alan Fern,

連結: http://proceedings.mlr.press/v80/greydanus18a.html

[182]. Learning Policy Representations in Multiagent Systems.

作者: Aditya Grover,Maruan Al-Shedivat,Jayesh K. Gupta,Yuri Burda,Harrison Edwards,

連結: http://proceedings.mlr.press/v80/grover18a.html

[183]. Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines.

作者: Bin Gu,Zhouyuan Huo,Cheng Deng,Heng Huang,

連結: http://proceedings.mlr.press/v80/gu18a.html

[184]. Learning to Search with MCTSnets.

作者: Arthur Guez,Theophane Weber,Ioannis Antonoglou,Karen Simonyan,Oriol Vinyals,Daan Wierstra,Rémi Munos,David Silver,

連結: http://proceedings.mlr.press/v80/guez18a.html

[185]. Characterizing Implicit Bias in Terms of Optimization Geometry.

作者: Suriya Gunasekar,Jason D. Lee,Daniel Soudry,Nathan Srebro,

連結: http://proceedings.mlr.press/v80/gunasekar18a.html

[186]. Shampoo: Preconditioned Stochastic Tensor Optimization.

作者: Vineet Gupta,Tomer Koren,Yoram Singer,

連結: http://proceedings.mlr.press/v80/gupta18a.html

[187]. Latent Space Policies for Hierarchical Reinforcement Learning.

作者: Tuomas Haarnoja,Kristian Hartikainen,Pieter Abbeel,Sergey Levine,

連結: http://proceedings.mlr.press/v80/haarnoja18a.html

[188]. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.

作者: Tuomas Haarnoja,Aurick Zhou,Pieter Abbeel,Sergey Levine,

連結: http://proceedings.mlr.press/v80/haarnoja18b.html

[189]. Comparison-Based Random Forests.

作者: Siavash Haghiri,Damien Garreau,Ulrike von Luxburg,

連結: http://proceedings.mlr.press/v80/haghiri18a.html

[190]. K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning.

作者: Jihun Hamm,Yung-Kyun Noh,

連結: http://proceedings.mlr.press/v80/hamm18a.html

[191]. Candidates vs. Noises Estimation for Large Multi-Class Classification Problem.

作者: Lei Han,Yiheng Huang,Tong Zhang,

連結: http://proceedings.mlr.press/v80/han18a.html

[192]. Stein Variational Gradient Descent Without Gradient.

作者: Jun Han,Qiang Liu,

連結: http://proceedings.mlr.press/v80/han18b.html

[193]. Rectify Heterogeneous Models with Semantic Mapping.

作者: Han-Jia Ye,De-Chuan Zhan,Yuan Jiang,Zhi-Hua Zhou,

連結: http://proceedings.mlr.press/v80/han-jia18a.html

[194]. Deep Models of Interactions Across Sets.

作者: Jason S. Hartford,Devon R. Graham,Kevin Leyton-Brown,Siamak Ravanbakhsh,

連結: http://proceedings.mlr.press/v80/hartford18a.html

[195]. Learning Memory Access Patterns.

作者: Milad Hashemi,Kevin Swersky,Jamie A. Smith,Grant Ayers,Heiner Litz,Jichuan Chang,Christos Kozyrakis,Parthasarathy Ranganathan,

連結: http://proceedings.mlr.press/v80/hashemi18a.html

[196]. Fairness Without Demographics in Repeated Loss Minimization.

作者: Tatsunori B. Hashimoto,Megha Srivastava,Hongseok Namkoong,Percy Liang,

連結: http://proceedings.mlr.press/v80/hashimoto18a.html

[197]. Multicalibration: Calibration for the (Computationally-Identifiable) Masses.

作者: Úrsula Hébert-Johnson,Michael P. Kim,Omer Reingold,Guy N. Rothblum,

連結: http://proceedings.mlr.press/v80/hebert-johnson18a.html

[198]. Recurrent Predictive State Policy Networks.

作者: Ahmed Hefny,Zita Marinho,Wen Sun,Siddhartha S. Srinivasa,Geoffrey J. Gordon,

連結: http://proceedings.mlr.press/v80/hefny18a.html

[199]. Learning unknown ODE models with Gaussian processes.

作者: Markus Heinonen,Cagatay Yildiz,Henrik Mannerström,Jukka Intosalmi,Harri Lähdesmäki,

連結: http://proceedings.mlr.press/v80/heinonen18a.html

[200]. Orthogonal Recurrent Neural Networks with Scaled Cayley Transform.

作者: Kyle Helfrich,Devin Willmott,Qiang Ye,

連結: http://proceedings.mlr.press/v80/helfrich18a.html

[201]. Fast Bellman Updates for Robust MDPs.

作者: Chin Pang Ho,Marek Petrik,Wolfram Wiesemann,

連結: http://proceedings.mlr.press/v80/ho18a.html

[202]. CyCADA: Cycle-Consistent Adversarial Domain Adaptation.

作者: Judy Hoffman,Eric Tzeng,Taesung Park,Jun-Yan Zhu,Phillip Isola,Kate Saenko,Alexei A. Efros,Trevor Darrell,

連結: http://proceedings.mlr.press/v80/hoffman18a.html

[203]. Sound Abstraction and Decomposition of Probabilistic Programs.

作者: Steven Holtzen,Guy Van den Broeck,Todd D. Millstein,

連結: http://proceedings.mlr.press/v80/holtzen18a.html

[204]. Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks.

作者: Mingyi Hong,Meisam Razaviyayn,Jason D. Lee,

連結: http://proceedings.mlr.press/v80/hong18a.html

[205]. Variational Bayesian dropout: pitfalls and fixes.

作者: Jiri Hron,Alexander G. de G. Matthews,Zoubin Ghahramani,

連結: http://proceedings.mlr.press/v80/hron18a.html

[206]. Does Distributionally Robust Supervised Learning Give Robust Classifiers?

作者: Weihua Hu,Gang Niu,Issei Sato,Masashi Sugiyama,

連結: http://proceedings.mlr.press/v80/hu18a.html

[207]. Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs.

作者: Bin Hu,Stephen Wright,Laurent Lessard,

連結: http://proceedings.mlr.press/v80/hu18b.html

[208]. Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices.

作者: Zengfeng Huang,

連結: http://proceedings.mlr.press/v80/huang18a.html

[209]. Learning Deep ResNet Blocks Sequentially using Boosting Theory.

作者: Furong Huang,Jordan T. Ash,John Langford,Robert E. Schapire,

連結: http://proceedings.mlr.press/v80/huang18b.html

[210]. Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling.

作者: Kejun Huang,Xiao Fu,Nicholas D. Sidiropoulos,

連結: http://proceedings.mlr.press/v80/huang18c.html

[211]. Neural Autoregressive Flows.

作者: Chin-Wei Huang,David Krueger,Alexandre Lacoste,Aaron C. Courville,

連結: http://proceedings.mlr.press/v80/huang18d.html

[212]. Topological Mixture Estimation.

作者: Steve Huntsman,

連結: http://proceedings.mlr.press/v80/huntsman18a.html

[213]. Decoupled Parallel Backpropagation with Convergence Guarantee.

作者: Zhouyuan Huo,Bin Gu,Qian Yang,Heng Huang,

連結: http://proceedings.mlr.press/v80/huo18a.html

[214]. Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning.

作者: Rodrigo Toro Icarte,Toryn Q. Klassen,Richard Anthony Valenzano,Sheila A. McIlraith,

連結: http://proceedings.mlr.press/v80/icarte18a.html

[215]. Deep Variational Reinforcement Learning for POMDPs.

作者: Maximilian Igl,Luisa M. Zintgraf,Tuan Anh Le,Frank Wood,Shimon Whiteson,

連結: http://proceedings.mlr.press/v80/igl18a.html

[216]. Attention-based Deep Multiple Instance Learning.

作者: Maximilian Ilse,Jakub M. Tomczak,Max Welling,

連結: http://proceedings.mlr.press/v80/ilse18a.html

[217]. Black-box Adversarial Attacks with Limited Queries and Information.

作者: Andrew Ilyas,Logan Engstrom,Anish Athalye,Jessy Lin,

連結: http://proceedings.mlr.press/v80/ilyas18a.html

[218]. Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model.

作者: Hideaki Imamura,Issei Sato,Masashi Sugiyama,

連結: http://proceedings.mlr.press/v80/imamura18a.html

[219]. Improving Regression Performance with Distributional Losses.

作者: Ehsan Imani,Martha White,

連結: http://proceedings.mlr.press/v80/imani18a.html

[220]. Deep Density Destructors.

作者: David I. Inouye,Pradeep Ravikumar,

連結: http://proceedings.mlr.press/v80/inouye18a.html

[221]. Unbiased Objective Estimation in Predictive Optimization.

作者: Shinji Ito,Akihiro Yabe,Ryohei Fujimaki,

連結: http://proceedings.mlr.press/v80/ito18a.html

[222]. Anonymous Walk Embeddings.

作者: Sergey Ivanov,Evgeny Burnaev,

連結: http://proceedings.mlr.press/v80/ivanov18a.html

[223]. Learning Binary Latent Variable Models: A Tensor Eigenpair Approach.

作者: Ariel Jaffe,Roi Weiss,Shai Carmi,Yuval Kluger,Boaz Nadler,

連結: http://proceedings.mlr.press/v80/jaffe18a.html

[224]. Firing Bandits: Optimizing Crowdfunding.

作者: Lalit Jain,Kevin G. Jamieson,

連結: http://proceedings.mlr.press/v80/jain18a.html

[225]. Differentially Private Matrix Completion Revisited.

作者: Prateek Jain,Om Dipakbhai Thakkar,Abhradeep Thakurta,

連結: http://proceedings.mlr.press/v80/jain18b.html

[226]. Video Prediction with Appearance and Motion Conditions.

作者: Yunseok Jang,Gunhee Kim,Yale Song,

連結: http://proceedings.mlr.press/v80/jang18a.html

[227]. Pathwise Derivatives Beyond the Reparameterization Trick.

作者: Martin Jankowiak,Fritz Obermeyer,

連結: http://proceedings.mlr.press/v80/jankowiak18a.html

[228]. Detecting non-causal artifacts in multivariate linear regression models.

作者: Dominik Janzing,Bernhard Schölkopf,

連結: http://proceedings.mlr.press/v80/janzing18a.html

[229]. A Unified Framework for Structured Low-rank Matrix Learning.

作者: Pratik Jawanpuria,Bamdev Mishra,

連結: http://proceedings.mlr.press/v80/jawanpuria18a.html

[230]. Efficient end-to-end learning for quantizable representations.

作者: Yeonwoo Jeong,Hyun Oh Song,

連結: http://proceedings.mlr.press/v80/jeong18a.html

[231]. Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks.

作者: Zhihao Jia,Sina Lin,Charles R. Qi,Alex Aiken,

連結: http://proceedings.mlr.press/v80/jia18a.html

[232]. Feedback-Based Tree Search for Reinforcement Learning.

作者: Daniel R. Jiang,Emmanuel Ekwedike,Han Liu,

連結: http://proceedings.mlr.press/v80/jiang18a.html

[233]. Quickshift++: Provably Good Initializations for Sample-Based Mean Shift.

作者: Heinrich Jiang,Jennifer Jang,Samory Kpotufe,

連結: http://proceedings.mlr.press/v80/jiang18b.html

[234]. MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels.

作者: Lu Jiang,Zhengyuan Zhou,Thomas Leung,Li-Jia Li,Li Fei-Fei,

連結: http://proceedings.mlr.press/v80/jiang18c.html

[235]. The Weighted Kendall and High-order Kernels for Permutations.

作者: Yunlong Jiao,Jean-Philippe Vert,

連結: http://proceedings.mlr.press/v80/jiao18a.html

[236]. Junction Tree Variational Autoencoder for Molecular Graph Generation.

作者: Wengong Jin,Regina Barzilay,Tommi S. Jaakkola,

連結: http://proceedings.mlr.press/v80/jin18a.html

[237]. Network Global Testing by Counting Graphlets.

作者: Jiashun Jin,Zheng Tracy Ke,Shengming Luo,

連結: http://proceedings.mlr.press/v80/jin18b.html

[238]. Regret Minimization for Partially Observable Deep Reinforcement Learning.

作者: Peter H. Jin,Kurt Keutzer,Sergey Levine,

連結: http://proceedings.mlr.press/v80/jin18c.html

[239]. WSNet: Compact and Efficient Networks Through Weight Sampling.

作者: Xiaojie Jin,Yingzhen Yang,Ning Xu,Jianchao Yang,Nebojsa Jojic,Jiashi Feng,Shuicheng Yan,

連結: http://proceedings.mlr.press/v80/jin18d.html

[240]. Large-Scale Cox Process Inference using Variational Fourier Features.

作者: S. T. John,James Hensman,

連結: http://proceedings.mlr.press/v80/john18a.html

[241]. Composite Functional Gradient Learning of Generative Adversarial Models.

作者: Rie Johnson,Tong Zhang,

連結: http://proceedings.mlr.press/v80/johnson18a.html

[242]. Kronecker Recurrent Units.

作者: Cijo Jose,Moustapha Cissé,François Fleuret,

連結: http://proceedings.mlr.press/v80/jose18a.html

[243]. Fast Decoding in Sequence Models Using Discrete Latent Variables.

作者: Lukasz Kaiser,Samy Bengio,Aurko Roy,Ashish Vaswani,Niki Parmar,Jakob Uszkoreit,Noam Shazeer,

連結: http://proceedings.mlr.press/v80/kaiser18a.html

[244]. Kernel Recursive ABC: Point Estimation with Intractable Likelihood.

作者: Takafumi Kajihara,Motonobu Kanagawa,Keisuke Yamazaki,Kenji Fukumizu,

連結: http://proceedings.mlr.press/v80/kajihara18a.html

[245]. Efficient Neural Audio Synthesis.

作者: Nal Kalchbrenner,Erich Elsen,Karen Simonyan,Seb Noury,Norman Casagrande,Edward Lockhart,Florian Stimberg,Aäron van den Oord,Sander Dieleman,Koray Kavukcuoglu,

連結: http://proceedings.mlr.press/v80/kalchbrenner18a.html

[246]. Learning Diffusion using Hyperparameters.

作者: Dimitris Kalimeris,Yaron Singer,Karthik Subbian,Udi Weinsberg,

連結: http://proceedings.mlr.press/v80/kalimeris18a.html

[247]. Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit.

作者: Sreejith Kallummil,Sheetal Kalyani,

連結: http://proceedings.mlr.press/v80/kallummil18a.html

[248]. Residual Unfairness in Fair Machine Learning from Prejudiced Data.

作者: Nathan Kallus,Angela Zhou,

連結: http://proceedings.mlr.press/v80/kallus18a.html

[249]. Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations.

作者: Ashwin Kalyan,Stefan Lee,Anitha Kannan,Dhruv Batra,

連結: http://proceedings.mlr.press/v80/kalyan18a.html

[250]. Semi-Supervised Learning via Compact Latent Space Clustering.

作者: Konstantinos Kamnitsas,Daniel C. Castro,Loïc Le Folgoc,Ian Walker,Ryutaro Tanno,Daniel Rueckert,Ben Glocker,Antonio Criminisi,Aditya V. Nori,

連結: http://proceedings.mlr.press/v80/kamnitsas18a.html

[251]. Policy Optimization with Demonstrations.

作者: Bingyi Kang,Zequn Jie,Jiashi Feng,

連結: http://proceedings.mlr.press/v80/kang18a.html

[252]. Improving Sign Random Projections With Additional Information.

作者: Keegan Kang,Wong Wei Pin,

連結: http://proceedings.mlr.press/v80/kang18b.html

[253]. Continual Reinforcement Learning with Complex Synapses.

作者: Christos Kaplanis,Murray Shanahan,Claudia Clopath,

連結: http://proceedings.mlr.press/v80/kaplanis18a.html

[254]. LaVAN: Localized and Visible Adversarial Noise.

作者: Danny Karmon,Daniel Zoran,Yoav Goldberg,

連結: http://proceedings.mlr.press/v80/karmon18a.html

[255]. Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis.

作者: Hiroyuki Kasai,Hiroyuki Sato,Bamdev Mishra,

連結: http://proceedings.mlr.press/v80/kasai18a.html

[256]. Not All Samples Are Created Equal: Deep Learning with Importance Sampling.

作者: Angelos Katharopoulos,François Fleuret,

連結: http://proceedings.mlr.press/v80/katharopoulos18a.html

[257]. Feasible Arm Identification.

作者: Julian Katz-Samuels,Clayton Scott,

連結: http://proceedings.mlr.press/v80/katz-samuels18a.html

[258]. Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints.

作者: Ehsan Kazemi,Morteza Zadimoghaddam,Amin Karbasi,

連結: http://proceedings.mlr.press/v80/kazemi18a.html

[259]. Focused Hierarchical RNNs for Conditional Sequence Processing.

作者: Nan Rosemary Ke,Konrad Zolna,Alessandro Sordoni,Zhouhan Lin,Adam Trischler,Yoshua Bengio,Joelle Pineau,Laurent Charlin,Christopher J. Pal,

連結: http://proceedings.mlr.press/v80/ke18a.html

[260]. Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness.

作者: Michael J. Kearns,Seth Neel,Aaron Roth,Zhiwei Steven Wu,

連結: http://proceedings.mlr.press/v80/kearns18a.html

[261]. Improved nearest neighbor search using auxiliary information and priority functions.

作者: Omid Keivani,Kaushik Sinha,

連結: http://proceedings.mlr.press/v80/keivani18a.html

[262]. ContextNet: Deep learning for Star Galaxy Classification.

作者: Noble Kennamer,David Kirkby,Alexander T. Ihler,Francisco Javier Sanchez-Lopez,

連結: http://proceedings.mlr.press/v80/kennamer18a.html

[263]. Convergence guarantees for a class of non-convex and non-smooth optimization problems.

作者: Koulik Khamaru,Martin J. Wainwright,

連結: http://proceedings.mlr.press/v80/khamaru18a.html

[264]. Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam.

作者: Mohammad Emtiyaz Khan,Didrik Nielsen,Voot Tangkaratt,Wu Lin,Yarin Gal,Akash Srivastava,

連結: http://proceedings.mlr.press/v80/khan18a.html

[265]. Geometry Score: A Method For Comparing Generative Adversarial Networks.

作者: Valentin Khrulkov,Ivan V. Oseledets,

連結: http://proceedings.mlr.press/v80/khrulkov18a.html

[266]. Blind Justice: Fairness with Encrypted Sensitive Attributes.

作者: Niki Kilbertus,Adrià Gascón,Matt J. Kusner,Michael Veale,Krishna P. Gummadi,Adrian Weller,

連結: http://proceedings.mlr.press/v80/kilbertus18a.html

[267]. Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data.

作者: Minyoung Kim,

連結: http://proceedings.mlr.press/v80/kim18a.html

[268]. Disentangling by Factorising.

作者: Hyunjik Kim,Andriy Mnih,

連結: http://proceedings.mlr.press/v80/kim18b.html

[269]. Self-Bounded Prediction Suffix Tree via Approximate String Matching.

作者: Dongwoo Kim,Christian J. Walder,

連結: http://proceedings.mlr.press/v80/kim18c.html

[270]. Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV).

作者: Been Kim,Martin Wattenberg,Justin Gilmer,Carrie J. Cai,James Wexler,Fernanda B. Viégas,Rory Sayres,

連結: http://proceedings.mlr.press/v80/kim18d.html

[271]. Semi-Amortized Variational Autoencoders.

作者: Yoon Kim,Sam Wiseman,Andrew C. Miller,David A. Sontag,Alexander M. Rush,

連結: http://proceedings.mlr.press/v80/kim18e.html

[272]. Neural Relational Inference for Interacting Systems.

作者: Thomas N. Kipf,Ethan Fetaya,Kuan-Chieh Wang,Max Welling,Richard S. Zemel,

連結: http://proceedings.mlr.press/v80/kipf18a.html

[273]. An Alternative View: When Does SGD Escape Local Minima?

作者: Robert Kleinberg,Yuanzhi Li,Yang Yuan,

連結: http://proceedings.mlr.press/v80/kleinberg18a.html

[274]. Crowdsourcing with Arbitrary Adversaries.

作者: Matthäus Kleindessner,Pranjal Awasthi,

連結: http://proceedings.mlr.press/v80/kleindessner18a.html

[275]. Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection.

作者: Jeremias Knoblauch,Theodoros Damoulas,

連結: http://proceedings.mlr.press/v80/knoblauch18a.html

[276]. Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework.

作者: Arman Sharifi Kolarijani,Peyman Mohajerin Esfahani,Tamás Keviczky,

連結: http://proceedings.mlr.press/v80/kolarijani18a.html

[277]. Nonconvex Optimization for Regression with Fairness Constraints.

作者: Junpei Komiyama,Akiko Takeda,Junya Honda,Hajime Shimao,

連結: http://proceedings.mlr.press/v80/komiyama18a.html

[278]. On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups.

作者: Risi Kondor,Shubhendu Trivedi,

連結: http://proceedings.mlr.press/v80/kondor18a.html

[279]. Compiling Combinatorial Prediction Games.

作者: Frédéric Koriche,

連結: http://proceedings.mlr.press/v80/koriche18a.html

[280]. Dynamic Evaluation of Neural Sequence Models.

作者: Ben Krause,Emmanuel Kahembwe,Iain Murray,Steve Renals,

連結: http://proceedings.mlr.press/v80/krause18a.html

[281]. Semiparametric Contextual Bandits.

作者: Akshay Krishnamurthy,Zhiwei Steven Wu,Vasilis Syrgkanis,

連結: http://proceedings.mlr.press/v80/krishnamurthy18a.html

[282]. Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice.

作者: Alan Kuhnle,J. David Smith,Victoria G. Crawford,My T. Thai,

連結: http://proceedings.mlr.press/v80/kuhnle18a.html

[283]. Accurate Uncertainties for Deep Learning Using Calibrated Regression.

作者: Volodymyr Kuleshov,Nathan Fenner,Stefano Ermon,

連結: http://proceedings.mlr.press/v80/kuleshov18a.html

[284]. Trainable Calibration Measures For Neural Networks From Kernel Mean Embeddings.

作者: Aviral Kumar,Sunita Sarawagi,Ujjwal Jain,

連結: http://proceedings.mlr.press/v80/kumar18a.html

[285]. Data-Dependent Stability of Stochastic Gradient Descent.

作者: Ilja Kuzborskij,Christoph H. Lampert,

連結: http://proceedings.mlr.press/v80/kuzborskij18a.html

[286]. Explicit Inductive Bias for Transfer Learning with Convolutional Networks.

作者: Xuhong Li,Yves Grandvalet,Franck Davoine,

連結: http://proceedings.mlr.press/v80/li18a.html

[287]. Understanding the Loss Surface of Neural Networks for Binary Classification.

作者: Shiyu Liang,Ruoyu Sun,Yixuan Li,Rayadurgam Srikant,

連結: http://proceedings.mlr.press/v80/liang18a.html

[288]. Mixed batches and symmetric discriminators for GAN training.

作者: Thomas Lucas,Corentin Tallec,Yann Ollivier,Jakob Verbeek,

連結: http://proceedings.mlr.press/v80/lucas18a.html

[289]. Binary Partitions with Approximate Minimum Impurity.

作者: Eduardo Sany Laber,Marco Molinaro,Felipe de A. Mello Pereira,

連結: http://proceedings.mlr.press/v80/laber18a.html

[290]. Canonical Tensor Decomposition for Knowledge Base Completion.

作者: Timothée Lacroix,Nicolas Usunier,Guillaume Obozinski,

連結: http://proceedings.mlr.press/v80/lacroix18a.html

[291]. Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks.

作者: Brenden M. Lake,Marco Baroni,

連結: http://proceedings.mlr.press/v80/lake18a.html

[292]. An Estimation and Analysis Framework for the Rasch Model.

作者: Andrew S. Lan,Mung Chiang,Christoph Studer,

連結: http://proceedings.mlr.press/v80/lan18a.html

[293]. Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering.

作者: Jan-Hendrik Lange,Andreas Karrenbauer,Bjoern Andres,

連結: http://proceedings.mlr.press/v80/lange18a.html

[294]. Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global.

作者: Thomas Laurent,James von Brecht,

連結: http://proceedings.mlr.press/v80/laurent18a.html

[295]. The Multilinear Structure of ReLU Networks.

作者: Thomas Laurent,James von Brecht,

連結: http://proceedings.mlr.press/v80/laurent18b.html

[296]. Hierarchical Imitation and Reinforcement Learning.

作者: Hoang Minh Le,Nan Jiang,Alekh Agarwal,Miroslav Dudík,Yisong Yue,Hal Daumé III,

連結: http://proceedings.mlr.press/v80/le18a.html

[297]. Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace.

作者: Yoonho Lee,Seungjin Choi,

連結: http://proceedings.mlr.press/v80/lee18a.html

[298]. Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling.

作者: Kyowoon Lee,Sol-A. Kim,Jaesik Choi,Seong-Whan Lee,

連結: http://proceedings.mlr.press/v80/lee18b.html

[299]. Gated Path Planning Networks.

作者: Lisa Lee,Emilio Parisotto,Devendra Singh Chaplot,Eric P. Xing,Ruslan Salakhutdinov,

連結: http://proceedings.mlr.press/v80/lee18c.html

[300]. Deep Asymmetric Multi-task Feature Learning.

作者: Haebeom Lee,Eunho Yang,Sung Ju Hwang,

連結: http://proceedings.mlr.press/v80/lee18d.html

[301]. Noise2Noise: Learning Image Restoration without Clean Data.

作者: Jaakko Lehtinen,Jacob Munkberg,Jon Hasselgren,Samuli Laine,Tero Karras,Miika Aittala,Timo Aila,

連結: http://proceedings.mlr.press/v80/lehtinen18a.html

[302]. Out-of-sample extension of graph adjacency spectral embedding.

作者: Keith Levin,Farbod Roosta-Khorasani,Michael W. Mahoney,Carey E. Priebe,

連結: http://proceedings.mlr.press/v80/levin18a.html

[303]. An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks.

作者: Qianxiao Li,Shuji Hao,

連結: http://proceedings.mlr.press/v80/li18b.html

[304]. Towards Binary-Valued Gates for Robust LSTM Training.

作者: Zhuohan Li,Di He,Fei Tian,Wei Chen,Tao Qin,Liwei Wang,Tie-Yan Liu,

連結: http://proceedings.mlr.press/v80/li18c.html

[305]. On the Limitations of First-Order Approximation in GAN Dynamics.

作者: Jerry Li,Aleksander Madry,John Peebles,Ludwig Schmidt,

連結: http://proceedings.mlr.press/v80/li18d.html

[306]. Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering.

作者: Pan Li,Olgica Milenkovic,

連結: http://proceedings.mlr.press/v80/li18e.html

[307]. The Well-Tempered Lasso.

作者: Yuanzhi Li,Yoram Singer,

連結: http://proceedings.mlr.press/v80/li18f.html

[308]. Estimation of Markov Chain via Rank-constrained Likelihood.

作者: Xudong Li,Mengdi Wang,Anru Zhang,

連結: http://proceedings.mlr.press/v80/li18g.html

[309]. Asynchronous Decentralized Parallel Stochastic Gradient Descent.

作者: Xiangru Lian,Wei Zhang,Ce Zhang,Ji Liu,

連結: http://proceedings.mlr.press/v80/lian18a.html

[310]. RLlib: Abstractions for Distributed Reinforcement Learning.

作者: Eric Liang,Richard Liaw,Robert Nishihara,Philipp Moritz,Roy Fox,Ken Goldberg,Joseph Gonzalez,Michael I. Jordan,Ion Stoica,

連結: http://proceedings.mlr.press/v80/liang18b.html

[311]. On the Spectrum of Random Features Maps of High Dimensional Data.

作者: Zhenyu Liao,Romain Couillet,

連結: http://proceedings.mlr.press/v80/liao18a.html

[312]. The Dynamics of Learning: A Random Matrix Approach.

作者: Zhenyu Liao,Romain Couillet,

連結: http://proceedings.mlr.press/v80/liao18b.html

[313]. Reviving and Improving Recurrent Back-Propagation.

作者: Renjie Liao,Yuwen Xiong,Ethan Fetaya,Lisa Zhang,KiJung Yoon,Xaq Pitkow,Raquel Urtasun,Richard S. Zemel,

連結: http://proceedings.mlr.press/v80/liao18c.html

[314]. Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods.

作者: Junhong Lin,Volkan Cevher,

連結: http://proceedings.mlr.press/v80/lin18a.html

[315]. Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces.

作者: Junhong Lin,Volkan Cevher,

連結: http://proceedings.mlr.press/v80/lin18b.html

[316]. Level-Set Methods for Finite-Sum Constrained Convex Optimization.

作者: Qihang Lin,Runchao Ma,Tianbao Yang,

連結: http://proceedings.mlr.press/v80/lin18c.html

[317]. Detecting and Correcting for Label Shift with Black Box Predictors.

作者: Zachary C. Lipton,Yu-Xiang Wang,Alexander J. Smola,

連結: http://proceedings.mlr.press/v80/lipton18a.html

[318]. Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression.

作者: Haitao Liu,Jianfei Cai,Yi Wang,Yew-Soon Ong,

連結: http://proceedings.mlr.press/v80/liu18a.html

[319]. Towards Black-box Iterative Machine Teaching.

作者: Weiyang Liu,Bo Dai,Xingguo Li,Zhen Liu,James M. Rehg,Le Song,

連結: http://proceedings.mlr.press/v80/liu18b.html

[320]. Delayed Impact of Fair Machine Learning.

作者: Lydia T. Liu,Sarah Dean,Esther Rolf,Max Simchowitz,Moritz Hardt,

連結: http://proceedings.mlr.press/v80/liu18c.html

[321]. A Two-Step Computation of the Exact GAN Wasserstein Distance.

作者: Huidong Liu,Xianfeng Gu,Dimitris Samaras,

連結: http://proceedings.mlr.press/v80/liu18d.html

[322]. Open Category Detection with PAC Guarantees.

作者: Si Liu,Risheek Garrepalli,Thomas G. Dietterich,Alan Fern,Dan Hendrycks,

連結: http://proceedings.mlr.press/v80/liu18e.html

[323]. Fast Variance Reduction Method with Stochastic Batch Size.

作者: Xuanqing Liu,Cho-Jui Hsieh,

連結: http://proceedings.mlr.press/v80/liu18f.html

[324]. Fast Stochastic AUC Maximization with O(1/n)-Convergence Rate.

作者: Mingrui Liu,Xiaoxuan Zhang,Zaiyi Chen,Xiaoyu Wang,Tianbao Yang,

連結: http://proceedings.mlr.press/v80/liu18g.html

[325]. On Matching Pursuit and Coordinate Descent.

作者: Francesco Locatello,Anant Raj,Sai Praneeth Karimireddy,Gunnar Rätsch,Bernhard Schölkopf,Sebastian U. Stich,Martin Jaggi,

連結: http://proceedings.mlr.press/v80/locatello18a.html

[326]. PDE-Net: Learning PDEs from Data.

作者: Zichao Long,Yiping Lu,Xianzhong Ma,Bin Dong,

連結: http://proceedings.mlr.press/v80/long18a.html

[327]. Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap.

作者: Miles E. Lopes,Shusen Wang,Michael W. Mahoney,

連結: http://proceedings.mlr.press/v80/lopes18a.html

[328]. Constraining the Dynamics of Deep Probabilistic Models.

作者: Marco Lorenzi,Maurizio Filippone,

連結: http://proceedings.mlr.press/v80/lorenzi18a.html

[329]. Spectrally Approximating Large Graphs with Smaller Graphs.

作者: Andreas Loukas,Pierre Vandergheynst,

連結: http://proceedings.mlr.press/v80/loukas18a.html

[330]. The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference.

作者: Hao Lu,Yuan Cao,Junwei Lu,Han Liu,Zhaoran Wang,

連結: http://proceedings.mlr.press/v80/lu18a.html

[331]. Accelerating Greedy Coordinate Descent Methods.

作者: Haihao Lu,Robert M. Freund,Vahab S. Mirrokni,

連結: http://proceedings.mlr.press/v80/lu18b.html

[332]. Structured Variationally Auto-encoded Optimization.

作者: Xiaoyu Lu,Javier Gonzalez,Zhenwen Dai,Neil D. Lawrence,

連結: http://proceedings.mlr.press/v80/lu18c.html

[333]. Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations.

作者: Yiping Lu,Aoxiao Zhong,Quanzheng Li,Bin Dong,

連結: http://proceedings.mlr.press/v80/lu18d.html

[334]. End-to-end Active Object Tracking via Reinforcement Learning.

作者: Wenhan Luo,Peng Sun,Fangwei Zhong,Wei Liu,Tong Zhang,Yizhou Wang,

連結: http://proceedings.mlr.press/v80/luo18a.html

[335]. Competitive Caching with Machine Learned Advice.

作者: Thodoris Lykouris,Sergei Vassilvitskii,

連結: http://proceedings.mlr.press/v80/lykouris18a.html

[336]. Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design.

作者: Wenlong Lyu,Fan Yang,Changhao Yan,Dian Zhou,Xuan Zeng,

連結: http://proceedings.mlr.press/v80/lyu18a.html

[337]. Celer: a Fast Solver for the Lasso with Dual Extrapolation.

作者: Mathurin Massias,Joseph Salmon,Alexandre Gramfort,

連結: http://proceedings.mlr.press/v80/massias18a.html

[338]. The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning.

作者: Siyuan Ma,Raef Bassily,Mikhail Belkin,

連結: http://proceedings.mlr.press/v80/ma18a.html

[339]. Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers.

作者: Yao Ma,Alexander Olshevsky,Csaba Szepesvári,Venkatesh Saligrama,

連結: http://proceedings.mlr.press/v80/ma18b.html

[340]. Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion.

作者: Cong Ma,Kaizheng Wang,Yuejie Chi,Yuxin Chen,

連結: http://proceedings.mlr.press/v80/ma18c.html

[341]. Dimensionality-Driven Learning with Noisy Labels.

作者: Xingjun Ma,Yisen Wang,Michael E. Houle,Shuo Zhou,Sarah M. Erfani,Shu-Tao Xia,Sudanthi N. R. Wijewickrema,James Bailey,

連結: http://proceedings.mlr.press/v80/ma18d.html

[342]. Approximate message passing for amplitude based optimization.

作者: Junjie Ma,Ji Xu,Arian Maleki,

連結: http://proceedings.mlr.press/v80/ma18e.html

[343]. Learning Adversarially Fair and Transferable Representations.

作者: David Madras,Elliot Creager,Toniann Pitassi,Richard S. Zemel,

連結: http://proceedings.mlr.press/v80/madras18a.html

[344]. An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning.

作者: Dhruv Malik,Malayandi Palaniappan,Jaime F. Fisac,Dylan Hadfield-Menell,Stuart J. Russell,Anca D. Dragan,

連結: http://proceedings.mlr.press/v80/malik18a.html

[345]. Iterative Amortized Inference.

作者: Joseph Marino,Yisong Yue,Stephan Mandt,

連結: http://proceedings.mlr.press/v80/marino18a.html

[346]. Streaming Principal Component Analysis in Noisy Settings.

作者: Teodor Vanislavov Marinov,Poorya Mianjy,Raman Arora,

連結: http://proceedings.mlr.press/v80/marinov18a.html

[347]. Fast Approximate Spectral Clustering for Dynamic Networks.

作者: Lionel Martin,Andreas Loukas,Pierre Vandergheynst,

連結: http://proceedings.mlr.press/v80/martin18a.html

[348]. Bayesian Model Selection for Change Point Detection and Clustering.

作者: Othmane Mazhar,Cristian R. Rojas,Carlo Fischione,Mohammad Reza Hesamzadeh,

連結: http://proceedings.mlr.press/v80/mazhar18a.html

[349]. Optimization, Fast and Slow: Optimally Switching between Local and Bayesian Optimization.

作者: Mark McLeod,Stephen J. Roberts,Michael A. Osborne,

連結: http://proceedings.mlr.press/v80/mcleod18a.html

[350]. Bounds on the Approximation Power of Feedforward Neural Networks.

作者: Mohammad Mehrabi,Aslan Tchamkerten,Mansoor I. Yousefi,

連結: http://proceedings.mlr.press/v80/mehrabi18a.html

[351]. Differentiable Dynamic Programming for Structured Prediction and Attention.

作者: Arthur Mensch,Mathieu Blondel,

連結: http://proceedings.mlr.press/v80/mensch18a.html

[352]. Ranking Distributions based on Noisy Sorting.

作者: Adil El Mesaoudi-Paul,Eyke Hüllermeier,Róbert Busa-Fekete,

連結: http://proceedings.mlr.press/v80/mesaoudi-paul18a.html

[353]. Which Training Methods for GANs do actually Converge?

作者: Lars M. Mescheder,Andreas Geiger,Sebastian Nowozin,

連結: http://proceedings.mlr.press/v80/mescheder18a.html

[354]. Configurable Markov Decision Processes.

作者: Alberto Maria Metelli,Mirco Mutti,Marcello Restelli,

連結: http://proceedings.mlr.press/v80/metelli18a.html

[355]. prDeep: Robust Phase Retrieval with a Flexible Deep Network.

作者: Christopher A. Metzler,Philip Schniter,Ashok Veeraraghavan,Richard G. Baraniuk,

連結: http://proceedings.mlr.press/v80/metzler18a.html

[356]. Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing-and Back.

作者: Elliot Meyerson,Risto Miikkulainen,

連結: http://proceedings.mlr.press/v80/meyerson18a.html

[357]. The Hidden Vulnerability of Distributed Learning in Byzantium.

作者: El Mahdi El Mhamdi,Rachid Guerraoui,Sébastien Rouault,

連結: http://proceedings.mlr.press/v80/mhamdi18a.html

[358]. On the Implicit Bias of Dropout.

作者: Poorya Mianjy,Raman Arora,René Vidal,

連結: http://proceedings.mlr.press/v80/mianjy18b.html

[359]. One-Shot Segmentation in Clutter.

作者: Claudio Michaelis,Matthias Bethge,Alexander S. Ecker,

連結: http://proceedings.mlr.press/v80/michaelis18a.html

[360]. Differentiable plasticity: training plastic neural networks with backpropagation.

作者: Thomas Miconi,Kenneth O. Stanley,Jeff Clune,

連結: http://proceedings.mlr.press/v80/miconi18a.html

[361]. Training Neural Machines with Trace-Based Supervision.

作者: Matthew Mirman,Dimitar I. Dimitrov,Pavle Djordjevic,Timon Gehr,Martin T. Vechev,

連結: http://proceedings.mlr.press/v80/mirman18a.html

[362]. Differentiable Abstract Interpretation for Provably Robust Neural Networks.

作者: Matthew Mirman,Timon Gehr,Martin T. Vechev,

連結: http://proceedings.mlr.press/v80/mirman18b.html

[363]. A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning.

作者: Konstantin Mishchenko,Franck Iutzeler,Jérôme Malick,Massih-Reza Amini,

連結: http://proceedings.mlr.press/v80/mishchenko18a.html

[364]. Data Summarization at Scale: A Two-Stage Submodular Approach.

作者: Marko Mitrovic,Ehsan Kazemi,Morteza Zadimoghaddam,Amin Karbasi,

連結: http://proceedings.mlr.press/v80/mitrovic18a.html

[365]. The Hierarchical Adaptive Forgetting Variational Filter.

作者: Vincent Moens,

連結: http://proceedings.mlr.press/v80/moens18a.html

[366]. Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings.

作者: Aryan Mokhtari,Hamed Hassani,Amin Karbasi,

連結: http://proceedings.mlr.press/v80/mokhtari18a.html

[367]. DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding.

作者: Thomas Moreau,Laurent Oudre,Nicolas Vayatis,

連結: http://proceedings.mlr.press/v80/moreau18a.html

[368]. WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models.

作者: Marine Le Morvan,Jean-Philippe Vert,

連結: http://proceedings.mlr.press/v80/morvan18a.html

[369]. Dropout Training, Data-dependent Regularization, and Generalization Bounds.

作者: Wenlong Mou,Yuchen Zhou,Jun Gao,Liwei Wang,

連結: http://proceedings.mlr.press/v80/mou18a.html

[370]. Kernelized Synaptic Weight Matrices.

作者: Lorenz K. Müller,Julien N. P. Martel,Giacomo Indiveri,

連結: http://proceedings.mlr.press/v80/muller18a.html

[371]. Rapid Adaptation with Conditionally Shifted Neurons.

作者: Tsendsuren Munkhdalai,Xingdi Yuan,Soroush Mehri,Adam Trischler,

連結: http://proceedings.mlr.press/v80/munkhdalai18a.html

[372]. On the Relationship between Data Efficiency and Error for Uncertainty Sampling.

作者: Stephen Mussmann,Percy Liang,

連結: http://proceedings.mlr.press/v80/mussmann18a.html

[373]. Fitting New Speakers Based on a Short Untranscribed Sample.

作者: Eliya Nachmani,Adam Polyak,Yaniv Taigman,Lior Wolf,

連結: http://proceedings.mlr.press/v80/nachmani18a.html

[374]. Smoothed Action Value Functions for Learning Gaussian Policies.

作者: Ofir Nachum,Mohammad Norouzi,George Tucker,Dale Schuurmans,

連結: http://proceedings.mlr.press/v80/nachum18a.html

[375]. Nearly Optimal Robust Subspace Tracking.

作者: Praneeth Narayanamurthy,Namrata Vaswani,

連結: http://proceedings.mlr.press/v80/narayanamurthy18a.html

[376]. Stochastic Proximal Algorithms for AUC Maximization.

作者: Michael Natole,Yiming Ying,Siwei Lyu,

連結: http://proceedings.mlr.press/v80/natole18a.html

[377]. Mitigating Bias in Adaptive Data Gathering via Differential Privacy.

作者: Seth Neel,Aaron Roth,

連結: http://proceedings.mlr.press/v80/neel18a.html

[378]. Optimization Landscape and Expressivity of Deep CNNs.

作者: Quynh Nguyen,Matthias Hein,

連結: http://proceedings.mlr.press/v80/nguyen18a.html

[379]. Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions.

作者: Quynh Nguyen,Mahesh Chandra Mukkamala,Matthias Hein,

連結: http://proceedings.mlr.press/v80/nguyen18b.html

[380]. SGD and Hogwild! Convergence Without the Bounded Gradients Assumption.

作者: Lam M. Nguyen,Phuong Ha Nguyen,Marten van Dijk,Peter Richtárik,Katya Scheinberg,Martin Takác,

連結: http://proceedings.mlr.press/v80/nguyen18c.html

[381]. Active Testing: An Efficient and Robust Framework for Estimating Accuracy.

作者: Phuc Xuan Nguyen,Deva Ramanan,Charless C. Fowlkes,

連結: http://proceedings.mlr.press/v80/nguyen18d.html

[382]. On Learning Sparsely Used Dictionaries from Incomplete Samples.

作者: Thanh V. Nguyen,Akshay Soni,Chinmay Hegde,

連結: http://proceedings.mlr.press/v80/nguyen18e.html

[383]. Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry.

作者: Maximilian Nickel,Douwe Kiela,

連結: http://proceedings.mlr.press/v80/nickel18a.html

[384]. State Space Gaussian Processes with Non-Gaussian Likelihood.

作者: Hannes Nickisch,Arno Solin,Alexander Grigorevskiy,

連結: http://proceedings.mlr.press/v80/nickisch18a.html

[385]. SparseMAP: Differentiable Sparse Structured Inference.

作者: Vlad Niculae,André F. T. Martins,Mathieu Blondel,Claire Cardie,

連結: http://proceedings.mlr.press/v80/niculae18a.html

[386]. A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations.

作者: Weili Nie,Yang Zhang,Ankit Patel,

連結: http://proceedings.mlr.press/v80/nie18a.html

[387]. Functional Gradient Boosting based on Residual Network Perception.

作者: Atsushi Nitanda,Taiji Suzuki,

連結: http://proceedings.mlr.press/v80/nitanda18a.html

[388]. Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams.

作者: Ashkan Norouzi-Fard,Jakub Tarnawski,Slobodan Mitrovic,Amir Zandieh,Aidasadat Mousavifar,Ola Svensson,

連結: http://proceedings.mlr.press/v80/norouzi-fard18a.html

[389]. Is Generator Conditioning Causally Related to GAN Performance?

作者: Augustus Odena,Jacob Buckman,Catherine Olsson,Tom B. Brown,Christopher Olah,Colin Raffel,Ian J. Goodfellow,

連結: http://proceedings.mlr.press/v80/odena18a.html

[390]. Learning in Reproducing Kernel Krein Spaces.

作者: Dino Oglic,Thomas Gärtner,

連結: http://proceedings.mlr.press/v80/oglic18a.html

[391]. BOCK : Bayesian Optimization with Cylindrical Kernels.

作者: ChangYong Oh,Efstratios Gavves,Max Welling,

連結: http://proceedings.mlr.press/v80/oh18a.html

[392]. Self-Imitation Learning.

作者: Junhyuk Oh,Yijie Guo,Satinder Singh,Honglak Lee,

連結: http://proceedings.mlr.press/v80/oh18b.html

[393]. A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks.

作者: Akifumi Okuno,Tetsuya Hada,Hidetoshi Shimodaira,

連結: http://proceedings.mlr.press/v80/okuno18a.html

[394]. Transformation Autoregressive Networks.

作者: Junier B. Oliva,Avinava Dubey,Manzil Zaheer,Barnabás Póczos,Ruslan Salakhutdinov,Eric P. Xing,Jeff Schneider,

連結: http://proceedings.mlr.press/v80/oliva18a.html

[395]. Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches.

作者: Simon Olofsson,Marc Peter Deisenroth,Ruth Misener,

連結: http://proceedings.mlr.press/v80/olofsson18a.html

[396]. Learning Localized Spatio-Temporal Models From Streaming Data.

作者: Muhammad Osama,Dave Zachariah,Thomas B. Schön,

連結: http://proceedings.mlr.press/v80/osama18a.html

[397]. Autoregressive Quantile Networks for Generative Modeling.

作者: Georg Ostrovski,Will Dabney,Rémi Munos,

連結: http://proceedings.mlr.press/v80/ostrovski18a.html

[398]. Efficient First-Order Algorithms for Adaptive Signal Denoising.

作者: Dmitrii Ostrovskii,Zaïd Harchaoui,

連結: http://proceedings.mlr.press/v80/ostrovskii18a.html

[399]. Learning Compact Neural Networks with Regularization.

作者: Samet Oymak,

連結: http://proceedings.mlr.press/v80/oymak18a.html

[400]. Tree Edit Distance Learning via Adaptive Symbol Embeddings.

作者: Benjamin Paaßen,Claudio Gallicchio,Alessio Micheli,Barbara Hammer,

連結: http://proceedings.mlr.press/v80/paassen18a.html

[401]. Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control.

作者: Yangchen Pan,Amir-massoud Farahmand,Martha White,Saleh Nabi,Piyush Grover,Daniel Nikovski,

連結: http://proceedings.mlr.press/v80/pan18a.html

[402]. Learning to Speed Up Structured Output Prediction.

作者: Xingyuan Pan,Vivek Srikumar,

連結: http://proceedings.mlr.press/v80/pan18b.html

[403]. Theoretical Analysis of Image-to-Image Translation with Adversarial Learning.

作者: Xudong Pan,Mi Zhang,Daizong Ding,

連結: http://proceedings.mlr.press/v80/pan18c.html

[404]. Max-Mahalanobis Linear Discriminant Analysis Networks.

作者: Tianyu Pang,Chao Du,Jun Zhu,

連結: http://proceedings.mlr.press/v80/pang18a.html

[405]. Stochastic Variance-Reduced Policy Gradient.

作者: Matteo Papini,Damiano Binaghi,Giuseppe Canonaco,Matteo Pirotta,Marcello Restelli,

連結: http://proceedings.mlr.press/v80/papini18a.html

[406]. Learning Independent Causal Mechanisms.

作者: Giambattista Parascandolo,Niki Kilbertus,Mateo Rojas-Carulla,Bernhard Schölkopf,

連結: http://proceedings.mlr.press/v80/parascandolo18a.html

[407]. Time Limits in Reinforcement Learning.

作者: Fabio Pardo,Arash Tavakoli,Vitaly Levdik,Petar Kormushev,

連結: http://proceedings.mlr.press/v80/pardo18a.html

[408]. Image Transformer.

作者: Niki Parmar,Ashish Vaswani,Jakob Uszkoreit,Lukasz Kaiser,Noam Shazeer,Alexander Ku,Dustin Tran,

連結: http://proceedings.mlr.press/v80/parmar18a.html

[409]. PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos.

作者: Paavo Parmas,Carl Edward Rasmussen,Jan Peters,Kenji Doya,

連結: http://proceedings.mlr.press/v80/parmas18a.html

[410]. High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach.

作者: Tim Pearce,Alexandra Brintrup,Mohamed Zaki,Andy Neely,

連結: http://proceedings.mlr.press/v80/pearce18a.html

[411]. Adaptive Three Operator Splitting.

作者: Fabian Pedregosa,Gauthier Gidel,

連結: http://proceedings.mlr.press/v80/pedregosa18a.html

[412]. Efficient Neural Architecture Search via Parameter Sharing.

作者: Hieu Pham,Melody Y. Guan,Barret Zoph,Quoc V. Le,Jeff Dean,

連結: http://proceedings.mlr.press/v80/pham18a.html

[413]. Bandits with Delayed, Aggregated Anonymous Feedback.

作者: Ciara Pike-Burke,Shipra Agrawal,Csaba Szepesvári,Steffen Grünewälder,

連結: http://proceedings.mlr.press/v80/pike-burke18a.html

[414]. Constant-Time Predictive Distributions for Gaussian Processes.

作者: Geoff Pleiss,Jacob R. Gardner,Kilian Q. Weinberger,Andrew Gordon Wilson,

連結: http://proceedings.mlr.press/v80/pleiss18a.html

[415]. Local Convergence Properties of SAGA/Prox-SVRG and Acceleration.

作者: Clarice Poon,Jingwei Liang,Carola-Bibiane Schoenlieb,

連結: http://proceedings.mlr.press/v80/poon18a.html

[416]. Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory.

作者: Guillaume Pouliot,

連結: http://proceedings.mlr.press/v80/pouliot18a.html

[417]. Learning Dynamics of Linear Denoising Autoencoders.

作者: Arnu Pretorius,Steve Kroon,Herman Kamper,

連結: http://proceedings.mlr.press/v80/pretorius18a.html

[418]. JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets.

作者: Yunchen Pu,Shuyang Dai,Zhe Gan,Weiyao Wang,Guoyin Wang,Yizhe Zhang,Ricardo Henao,Lawrence Carin,

連結: http://proceedings.mlr.press/v80/pu18a.html

[419]. Selecting Representative Examples for Program Synthesis.

作者: Yewen Pu,Zachery Miranda,Armando Solar-Lezama,Leslie Pack Kaelbling,

連結: http://proceedings.mlr.press/v80/pu18b.html

[420]. Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction.

作者: Siyuan Qi,Baoxiong Jia,Song-Chun Zhu,

連結: http://proceedings.mlr.press/v80/qi18a.html

[421]. Do Outliers Ruin Collaboration?

作者: Mingda Qiao,

連結: http://proceedings.mlr.press/v80/qiao18a.html

[422]. Gradually Updated Neural Networks for Large-Scale Image Recognition.

作者: Siyuan Qiao,Zhishuai Zhang,Wei Shen,Bo Wang,Alan L. Yuille,

連結: http://proceedings.mlr.press/v80/qiao18b.html

[423]. DCFNet: Deep Neural Network with Decomposed Convolutional Filters.

作者: Qiang Qiu,Xiuyuan Cheng,A. Robert Calderbank,Guillermo Sapiro,

連結: http://proceedings.mlr.press/v80/qiu18a.html

[424]. Non-convex Conditional Gradient Sliding.

作者: Chao Qu,Yan Li,Huan Xu,

連結: http://proceedings.mlr.press/v80/qu18a.html

[425]. Machine Theory of Mind.

作者: Neil C. Rabinowitz,Frank Perbet,H. Francis Song,Chiyuan Zhang,S. M. Ali Eslami,Matthew Botvinick,

連結: http://proceedings.mlr.press/v80/rabinowitz18a.html

[426]. Fast Parametric Learning with Activation Memorization.

作者: Jack W. Rae,Chris Dyer,Peter Dayan,Timothy P. Lillicrap,

連結: http://proceedings.mlr.press/v80/rae18a.html

[427]. Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

作者: Maithra Raghu,Alex Irpan,Jacob Andreas,Robert Kleinberg,Quoc V. Le,Jon M. Kleinberg,

連結: http://proceedings.mlr.press/v80/raghu18a.html

[428]. Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation.

作者: Hugo Raguet,Loïc Landrieu,

連結: http://proceedings.mlr.press/v80/raguet18a.html

[429]. Modeling Others using Oneself in Multi-Agent Reinforcement Learning.

作者: Roberta Raileanu,Emily Denton,Arthur Szlam,Rob Fergus,

連結: http://proceedings.mlr.press/v80/raileanu18a.html

[430]. On Nesting Monte Carlo Estimators.

作者: Tom Rainforth,Robert Cornish,Hongseok Yang,Andrew Warrington,

連結: http://proceedings.mlr.press/v80/rainforth18a.html

[431]. Tighter Variational Bounds are Not Necessarily Better.

作者: Tom Rainforth,Adam R. Kosiorek,Tuan Anh Le,Chris J. Maddison,Maximilian Igl,Frank Wood,Yee Whye Teh,

連結: http://proceedings.mlr.press/v80/rainforth18b.html

[432]. SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate.

作者: Aaditya Ramdas,Tijana Zrnic,Martin J. Wainwright,Michael I. Jordan,

連結: http://proceedings.mlr.press/v80/ramdas18a.html

[433]. QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.

作者: Tabish Rashid,Mikayel Samvelyan,Christian Schröder de Witt,Gregory Farquhar,Jakob N. Foerster,Shimon Whiteson,

連結: http://proceedings.mlr.press/v80/rashid18a.html

[434]. Gradient Coding from Cyclic MDS Codes and Expander Graphs.

作者: Netanel Raviv,Rashish Tandon,Alex Dimakis,Itzhak Tamo,

連結: http://proceedings.mlr.press/v80/raviv18a.html

[435]. Learning Implicit Generative Models with the Method of Learned Moments.

作者: Suman V. Ravuri,Shakir Mohamed,Mihaela Rosca,Oriol Vinyals,

連結: http://proceedings.mlr.press/v80/ravuri18a.html

[436]. Weightless: Lossy weight encoding for deep neural network compression.

作者: Brandon Reagen,Udit Gupta,Bob Adolf,Michael Mitzenmacher,Alexander M. Rush,Gu-Yeon Wei,David Brooks,

連結: http://proceedings.mlr.press/v80/reagan18a.html

[437]. Learning to Reweight Examples for Robust Deep Learning.

作者: Mengye Ren,Wenyuan Zeng,Bin Yang,Raquel Urtasun,

連結: http://proceedings.mlr.press/v80/ren18a.html

[438]. Learning by Playing Solving Sparse Reward Tasks from Scratch.

作者: Martin A. Riedmiller,Roland Hafner,Thomas Lampe,Michael Neunert,Jonas Degrave,Tom Van de Wiele,Vlad Mnih,Nicolas Heess,Jost Tobias Springenberg,

連結: http://proceedings.mlr.press/v80/riedmiller18a.html

[439]. Been There, Done That: Meta-Learning with Episodic Recall.

作者: Samuel Ritter,Jane X. Wang,Zeb Kurth-Nelson,Siddhant M. Jayakumar,Charles Blundell,Razvan Pascanu,Matthew Botvinick,

連結: http://proceedings.mlr.press/v80/ritter18a.html

[440]. A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music.

作者: Adam Roberts,Jesse H. Engel,Colin Raffel,Curtis Hawthorne,Douglas Eck,

連結: http://proceedings.mlr.press/v80/roberts18a.html

[441]. Learning to Optimize Combinatorial Functions.

作者: Nir Rosenfeld,Eric Balkanski,Amir Globerson,Yaron Singer,

連結: http://proceedings.mlr.press/v80/rosenfeld18a.html

[442]. Fast Information-theoretic Bayesian Optimisation.

作者: Bin Xin Ru,Mark McLeod,Diego Granziol,Michael A. Osborne,

連結: http://proceedings.mlr.press/v80/ru18a.html

[443]. Deep One-Class Classification.

作者: Lukas Ruff,Nico Görnitz,Lucas Deecke,Shoaib Ahmed Siddiqui,Robert A. Vandermeulen,Alexander Binder,Emmanuel Müller,Marius Kloft,

連結: http://proceedings.mlr.press/v80/ruff18a.html

[444]. Augment and Reduce: Stochastic Inference for Large Categorical Distributions.

作者: Francisco J. R. Ruiz,Michalis K. Titsias,Adji B. Dieng,David M. Blei,

連結: http://proceedings.mlr.press/v80/ruiz18a.html

[445]. Probabilistic Boolean Tensor Decomposition.

作者: Tammo Rukat,Christopher C. Holmes,Christopher Yau,

連結: http://proceedings.mlr.press/v80/rukat18a.html

[446]. Black-Box Variational Inference for Stochastic Differential Equations.

作者: Thomas Ryder,Andrew Golightly,A. Stephen McGough,Dennis Prangle,

連結: http://proceedings.mlr.press/v80/ryder18a.html

[447]. Spurious Local Minima are Common in Two-Layer ReLU Neural Networks.

作者: Itay Safran,Ohad Shamir,

連結: http://proceedings.mlr.press/v80/safran18a.html

[448]. Learning Equations for Extrapolation and Control.

作者: Subham S. Sahoo,Christoph H. Lampert,Georg Martius,

連結: http://proceedings.mlr.press/v80/sahoo18a.html

[449]. Tempered Adversarial Networks.

作者: Mehdi S. M. Sajjadi,Giambattista Parascandolo,Arash Mehrjou,Bernhard Schölkopf,

連結: http://proceedings.mlr.press/v80/sajjadi18a.html

[450]. Representation Tradeoffs for Hyperbolic Embeddings.

作者: Frederic Sala,Christopher De Sa,Albert Gu,Christopher Ré,

連結: http://proceedings.mlr.press/v80/sala18a.html

[451]. Graph Networks as Learnable Physics Engines for Inference and Control.

作者: Alvaro Sanchez-Gonzalez,Nicolas Heess,Jost Tobias Springenberg,Josh Merel,Martin A. Riedmiller,Raia Hadsell,Peter W. Battaglia,

連結: http://proceedings.mlr.press/v80/sanchez-gonzalez18a.html

[452]. Measuring abstract reasoning in neural networks.

作者: Adam Santoro,Felix Hill,David G. T. Barrett,Ari S. Morcos,Timothy P. Lillicrap,

連結: http://proceedings.mlr.press/v80/santoro18a.html

[453]. A Classification-Based Study of Covariate Shift in GAN Distributions.

作者: Shibani Santurkar,Ludwig Schmidt,Aleksander Madry,

連結: http://proceedings.mlr.press/v80/santurkar18a.html

[454]. TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service.

作者: Amartya Sanyal,Matt J. Kusner,Adrià Gascón,Varun Kanade,

連結: http://proceedings.mlr.press/v80/sanyal18a.html

[455]. Tight Regret Bounds for Bayesian Optimization in One Dimension.

作者: Jonathan Scarlett,

連結: http://proceedings.mlr.press/v80/scarlett18a.html

[456]. Learning with Abandonment.

作者: Sven Schmit,Ramesh Johari,

連結: http://proceedings.mlr.press/v80/schmit18a.html

[457]. Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care.

作者: Patrick Schwab,Emanuela Keller,Carl Muroi,David J. Mack,Christian Strässle,Walter Karlen,

連結: http://proceedings.mlr.press/v80/schwab18a.html

[458]. Progress & Compress: A scalable framework for continual learning.

作者: Jonathan Schwarz,Wojciech Czarnecki,Jelena Luketina,Agnieszka Grabska-Barwinska,Yee Whye Teh,Razvan Pascanu,Raia Hadsell,

連結: http://proceedings.mlr.press/v80/schwarz18a.html

[459]. Multi-Fidelity Black-Box Optimization with Hierarchical Partitions.

作者: Rajat Sen,Kirthevasan Kandasamy,Sanjay Shakkottai,

連結: http://proceedings.mlr.press/v80/sen18a.html

[460]. Overcoming Catastrophic Forgetting with Hard Attention to the Task.

作者: Joan Serrà,Didac Suris,Marius Miron,Alexandros Karatzoglou,

連結: http://proceedings.mlr.press/v80/serra18a.html

[461]. Bounding and Counting Linear Regions of Deep Neural Networks.

作者: Thiago Serra,Christian Tjandraatmadja,Srikumar Ramalingam,

連結: http://proceedings.mlr.press/v80/serra18b.html

[462]. First Order Generative Adversarial Networks.

作者: Calvin Seward,Thomas Unterthiner,Urs Bergmann,Nikolay Jetchev,Sepp Hochreiter,

連結: http://proceedings.mlr.press/v80/seward18a.html

[463]. Finding Influential Training Samples for Gradient Boosted Decision Trees.

作者: Boris Sharchilev,Yury Ustinovskiy,Pavel Serdyukov,Maarten de Rijke,

連結: http://proceedings.mlr.press/v80/sharchilev18a.html

[464]. Solving Partial Assignment Problems using Random Clique Complexes.

作者: Charu Sharma,Deepak Nathani,Manohar Kaul,

連結: http://proceedings.mlr.press/v80/sharma18a.html

[465]. Adafactor: Adaptive Learning Rates with Sublinear Memory Cost.

作者: Noam Shazeer,Mitchell Stern,

連結: http://proceedings.mlr.press/v80/shazeer18a.html

[466]. Locally Private Hypothesis Testing.

作者: Or Sheffet,

連結: http://proceedings.mlr.press/v80/sheffet18a.html

[467]. Learning in Integer Latent Variable Models with Nested Automatic Differentiation.

作者: Daniel Sheldon,Kevin Winner,Debora Sujono,

連結: http://proceedings.mlr.press/v80/sheldon18a.html

[468]. Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication.

作者: Zebang Shen,Aryan Mokhtari,Tengfei Zhou,Peilin Zhao,Hui Qian,

連結: http://proceedings.mlr.press/v80/shen18a.html

[469]. An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method.

作者: Li Shen,Peng Sun,Yitong Wang,Wei Liu,Tong Zhang,

連結: http://proceedings.mlr.press/v80/shen18b.html

[470]. A Spectral Approach to Gradient Estimation for Implicit Distributions.

作者: Jiaxin Shi,Shengyang Sun,Jun Zhu,

連結: http://proceedings.mlr.press/v80/shi18a.html

[471]. TACO: Learning Task Decomposition via Temporal Alignment for Control.

作者: Kyriacos Shiarlis,Markus Wulfmeier,Sasha Salter,Shimon Whiteson,Ingmar Posner,

連結: http://proceedings.mlr.press/v80/shiarlis18a.html

[472]. CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning.

作者: Wissam Siblini,Frank Meyer,Pascale Kuntz,

連結: http://proceedings.mlr.press/v80/siblini18a.html

[473]. Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization.

作者: Umut Simsekli,Cagatay Yildiz,Thanh Huy Nguyen,A. Taylan Cemgil,Gaël Richard,

連結: http://proceedings.mlr.press/v80/simsekli18a.html

[474]. K-means clustering using random matrix sparsification.

作者: Kaushik Sinha,

連結: http://proceedings.mlr.press/v80/sinha18a.html

[475]. Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron.

作者: R. J. Skerry-Ryan,Eric Battenberg,Ying Xiao,Yuxuan Wang,Daisy Stanton,Joel Shor,Ron J. Weiss,Rob Clark,Rif A. Saurous,

連結: http://proceedings.mlr.press/v80/skerry-ryan18a.html

[476]. An Inference-Based Policy Gradient Method for Learning Options.

作者: Matthew Smith,Herke van Hoof,Joelle Pineau,

連結: http://proceedings.mlr.press/v80/smith18a.html

[477]. Accelerating Natural Gradient with Higher-Order Invariance.

作者: Yang Song,Jiaming Song,Stefano Ermon,

連結: http://proceedings.mlr.press/v80/song18a.html

[478]. Knowledge Transfer with Jacobian Matching.

作者: Suraj Srinivas,François Fleuret,

連結: http://proceedings.mlr.press/v80/srinivas18a.html

[479]. Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control.

作者: Aravind Srinivas,Allan Jabri,Pieter Abbeel,Sergey Levine,Chelsea Finn,

連結: http://proceedings.mlr.press/v80/srinivas18b.html

[480]. Structured Control Nets for Deep Reinforcement Learning.

作者: Mario Srouji,Jian Zhang,Ruslan Salakhutdinov,

連結: http://proceedings.mlr.press/v80/srouji18a.html

[481]. Approximation Algorithms for Cascading Prediction Models.

作者: Matthew Streeter,

連結: http://proceedings.mlr.press/v80/streeter18a.html

[482]. Learning Low-Dimensional Temporal Representations.

作者: Bing Su,Ying Wu,

連結: http://proceedings.mlr.press/v80/su18a.html

[483]. Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search.

作者: Masanori Suganuma,Mete Ozay,Takayuki Okatani,

連結: http://proceedings.mlr.press/v80/suganuma18a.html

[484]. Stagewise Safe Bayesian Optimization with Gaussian Processes.

作者: Yanan Sui,Vincent Zhuang,Joel W. Burdick,Yisong Yue,

連結: http://proceedings.mlr.press/v80/sui18a.html

[485]. Neural Program Synthesis from Diverse Demonstration Videos.

作者: Shao-Hua Sun,Hyeonwoo Noh,Sriram Somasundaram,Joseph J. Lim,

連結: http://proceedings.mlr.press/v80/sun18a.html

[486]. Scalable Approximate Bayesian Inference for Particle Tracking Data.

作者: Ruoxi Sun,Liam Paninski,

連結: http://proceedings.mlr.press/v80/sun18b.html

[487]. Graphical Nonconvex Optimization via an Adaptive Convex Relaxation.

作者: Qiang Sun,Kean Ming Tan,Han Liu,Tong Zhang,

連結: http://proceedings.mlr.press/v80/sun18c.html

[488]. Convolutional Imputation of Matrix Networks.

作者: Qingyun Sun,Mengyuan Yan,David L. Donoho,Stephen P. Boyd,

連結: http://proceedings.mlr.press/v80/sun18d.html

[489]. Differentiable Compositional Kernel Learning for Gaussian Processes.

作者: Shengyang Sun,Guodong Zhang,Chaoqi Wang,Wenyuan Zeng,Jiaman Li,Roger B. Grosse,

連結: http://proceedings.mlr.press/v80/sun18e.html

[490]. Learning the Reward Function for a Misspecified Model.

作者: Erik Talvitie,

連結: http://proceedings.mlr.press/v80/talvitie18a.html

[491]. D2: Decentralized Training over Decentralized Data.

作者: Hanlin Tang,Xiangru Lian,Ming Yan,Ce Zhang,Ji Liu,

連結: http://proceedings.mlr.press/v80/tang18a.html

[492]. Neural Inverse Rendering for General Reflectance Photometric Stereo.

作者: Tatsunori Taniai,Takanori Maehara,

連結: http://proceedings.mlr.press/v80/taniai18a.html

[493]. Black Box FDR.

作者: Wesley Tansey,Yixin Wang,David M. Blei,Raul Rabadan,

連結: http://proceedings.mlr.press/v80/tansey18a.html

[494]. Best Arm Identification in Linear Bandits with Linear Dimension Dependency.

作者: Chao Tao,Saúl A. Blanco,Yuan Zhou,

連結: http://proceedings.mlr.press/v80/tao18a.html

[495]. Chi-square Generative Adversarial Network.

作者: Chenyang Tao,Liqun Chen,Ricardo Henao,Jianfeng Feng,Lawrence Carin,

連結: http://proceedings.mlr.press/v80/tao18b.html

[496]. Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees.

作者: Adrien Taylor,Bryan Van Scoy,Laurent Lessard,

連結: http://proceedings.mlr.press/v80/taylor18a.html

[497]. Bayesian Uncertainty Estimation for Batch Normalized Deep Networks.

作者: Mattias Teye,Hossein Azizpour,Kevin Smith,

連結: http://proceedings.mlr.press/v80/teye18a.html

[498]. Decoupling Gradient-Like Learning Rules from Representations.

作者: Philip S. Thomas,Christoph Dann,Emma Brunskill,

連結: http://proceedings.mlr.press/v80/thomas18a.html

[499]. CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions.

作者: Kevin Tian,Teng Zhang,James Zou,

連結: http://proceedings.mlr.press/v80/tian18a.html

[500]. Importance Weighted Transfer of Samples in Reinforcement Learning.

作者: Andrea Tirinzoni,Andrea Sessa,Matteo Pirotta,Marcello Restelli,

連結: http://proceedings.mlr.press/v80/tirinzoni18a.html

[501]. Adversarial Regression with Multiple Learners.

作者: Liang Tong,Sixie Yu,Scott Alfeld,Yevgeniy Vorobeychik,

連結: http://proceedings.mlr.press/v80/tong18a.html

[502]. Convergent TREE BACKUP and RETRACE with Function Approximation.

作者: Ahmed Touati,Pierre-Luc Bacon,Doina Precup,Pascal Vincent,

連結: http://proceedings.mlr.press/v80/touati18a.html

[503]. Learning Longer-term Dependencies in RNNs with Auxiliary Losses.

作者: Trieu H. Trinh,Andrew M. Dai,Thang Luong,Quoc V. Le,

連結: http://proceedings.mlr.press/v80/trinh18a.html

[504]. Theoretical Analysis of Sparse Subspace Clustering with Missing Entries.

作者: Manolis C. Tsakiris,René Vidal,

連結: http://proceedings.mlr.press/v80/tsakiris18a.html

[505]. StrassenNets: Deep Learning with a Multiplication Budget.

作者: Michael Tschannen,Aran Khanna,Animashree Anandkumar,

連結: http://proceedings.mlr.press/v80/tschannen18a.html

[506]. Invariance of Weight Distributions in Rectified MLPs.

作者: Russell Tsuchida,Farbod Roosta-Khorasani,Marcus Gallagher,

連結: http://proceedings.mlr.press/v80/tsuchida18a.html

[507]. Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator.

作者: Stephen Tu,Benjamin Recht,

連結: http://proceedings.mlr.press/v80/tu18a.html

[508]. The Mirage of Action-Dependent Baselines in Reinforcement Learning.

作者: George Tucker,Surya Bhupatiraju,Shixiang Gu,Richard E. Turner,Zoubin Ghahramani,Sergey Levine,

連結: http://proceedings.mlr.press/v80/tucker18a.html

[509]. DVAE++: Discrete Variational Autoencoders with Overlapping Transformations.

作者: Arash Vahdat,William G. Macready,Zhengbing Bian,Amir Khoshaman,Evgeny Andriyash,

連結: http://proceedings.mlr.press/v80/vahdat18a.html

[510]. Programmatically Interpretable Reinforcement Learning.

作者: Abhinav Verma,Vijayaraghavan Murali,Rishabh Singh,Pushmeet Kohli,Swarat Chaudhuri,

連結: http://proceedings.mlr.press/v80/verma18a.html

[511]. A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization.

作者: Robin Vogel,Aurélien Bellet,Stéphan Clémençon,

連結: http://proceedings.mlr.press/v80/vogel18a.html

[512]. Transfer Learning via Learning to Transfer.

作者: Ying Wei,Yu Zhang,Junzhou Huang,Qiang Yang,

連結: http://proceedings.mlr.press/v80/wei18a.html

[513]. Semi-Supervised Learning on Data Streams via Temporal Label Propagation.

作者: Tal Wagner,Sudipto Guha,Shiva Prasad Kasiviswanathan,Nina Mishra,

連結: http://proceedings.mlr.press/v80/wagner18a.html

[514]. Neural Dynamic Programming for Musical Self Similarity.

作者: Christian J. Walder,Dongwoo Kim,

連結: http://proceedings.mlr.press/v80/walder18a.html

[515]. Thompson Sampling for Combinatorial Semi-Bandits.

作者: Siwei Wang,Wei Chen,

連結: http://proceedings.mlr.press/v80/wang18a.html

[516]. PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning.

作者: Yunbo Wang,Zhifeng Gao,Mingsheng Long,Jianmin Wang,Philip S. Yu,

連結: http://proceedings.mlr.press/v80/wang18b.html

[517]. Analyzing the Robustness of Nearest Neighbors to Adversarial Examples.

作者: Yizhen Wang,Somesh Jha,Kamalika Chaudhuri,

連結: http://proceedings.mlr.press/v80/wang18c.html

[518]. Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations.

作者: Xingyu Wang,Diego Klabjan,

連結: http://proceedings.mlr.press/v80/wang18d.html

[519]. Coded Sparse Matrix Multiplication.

作者: Sinong Wang,Jiashang Liu,Ness B. Shroff,

連結: http://proceedings.mlr.press/v80/wang18e.html

[520]. A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models.

作者: Beilun Wang,Arshdeep Sekhon,Yanjun Qi,

連結: http://proceedings.mlr.press/v80/wang18f.html

[521]. Provable Variable Selection for Streaming Features.

作者: Jing Wang,Jie Shen,Ping Li,

連結: http://proceedings.mlr.press/v80/wang18g.html

[522]. Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis.

作者: Yuxuan Wang,Daisy Stanton,Yu Zhang,R. J. Skerry-Ryan,Eric Battenberg,Joel Shor,Ying Xiao,Ye Jia,Fei Ren,Rif A. Saurous,

連結: http://proceedings.mlr.press/v80/wang18h.html

[523]. Adversarial Distillation of Bayesian Neural Network Posteriors.

作者: Kuan-Chieh Wang,Paul Vicol,James Lucas,Li Gu,Roger B. Grosse,Richard S. Zemel,

連結: http://proceedings.mlr.press/v80/wang18i.html

[524]. Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Convariates.

作者: Xue Wang,Mike Mingcheng Wei,Tao Yao,

連結: http://proceedings.mlr.press/v80/wang18j.html

[525]. Online Convolutional Sparse Coding with Sample-Dependent Dictionary.

作者: Yaqing Wang,Quanming Yao,James Tin-Yau Kwok,Lionel M. Ni,

連結: http://proceedings.mlr.press/v80/wang18k.html

[526]. Stein Variational Message Passing for Continuous Graphical Models.

作者: Dilin Wang,Zhe Zeng,Qiang Liu,

連結: http://proceedings.mlr.press/v80/wang18l.html

[527]. Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions.

作者: Shuaiwen Wang,Wenda Zhou,Haihao Lu,Arian Maleki,Vahab S. Mirrokni,

連結: http://proceedings.mlr.press/v80/wang18m.html

[528]. Hierarchical Multi-Label Classification Networks.

作者: Jonatas Wehrmann,Ricardo Cerri,Rodrigo C. Barros,

連結: http://proceedings.mlr.press/v80/wehrmann18a.html

[529]. Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks.

作者: Daphna Weinshall,Gad Cohen,Dan Amir,

連結: http://proceedings.mlr.press/v80/weinshall18a.html

[530]. Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples.

作者: Gail Weiss,Yoav Goldberg,Eran Yahav,

連結: http://proceedings.mlr.press/v80/weiss18a.html

[531]. LEAPSANDBOUNDS: A Method for Approximately Optimal Algorithm Configuration.

作者: Gellért Weisz,András György,Csaba Szepesvári,

連結: http://proceedings.mlr.press/v80/weisz18a.html

[532]. Deep Predictive Coding Network for Object Recognition.

作者: Haiguang Wen,Kuan Han,Junxing Shi,Yizhen Zhang,Eugenio Culurciello,Zhongming Liu,

連結: http://proceedings.mlr.press/v80/wen18a.html

[533]. Towards Fast Computation of Certified Robustness for ReLU Networks.

作者: Tsui-Wei Weng,Huan Zhang,Hongge Chen,Zhao Song,Cho-Jui Hsieh,Luca Daniel,Duane S. Boning,Inderjit S. Dhillon,

連結: http://proceedings.mlr.press/v80/weng18a.html

[534]. Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope.

作者: Eric Wong,J. Zico Kolter,

連結: http://proceedings.mlr.press/v80/wong18a.html

[535]. Local Density Estimation in High Dimensions.

作者: Xian Wu,Moses Charikar,Vishnu Natchu,

連結: http://proceedings.mlr.press/v80/wu18a.html

[536]. Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits.

作者: Huasen Wu,Xueying Guo,Xin Liu,

連結: http://proceedings.mlr.press/v80/wu18b.html

[537]. SQL-Rank: A Listwise Approach to Collaborative Ranking.

作者: Liwei Wu,Cho-Jui Hsieh,James Sharpnack,

連結: http://proceedings.mlr.press/v80/wu18c.html

[538]. Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization.

作者: Jiaxiang Wu,Weidong Huang,Junzhou Huang,Tong Zhang,

連結: http://proceedings.mlr.press/v80/wu18d.html

[539]. Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training.

作者: Xi Wu,Uyeong Jang,Jiefeng Chen,Lingjiao Chen,Somesh Jha,

連結: http://proceedings.mlr.press/v80/wu18e.html

[540]. Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms.

作者: Yi Wu,Siddharth Srivastava,Nicholas Hay,Simon Du,Stuart J. Russell,

連結: http://proceedings.mlr.press/v80/wu18f.html

[541]. Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization.

作者: Hang Wu,May D. Wang,

連結: http://proceedings.mlr.press/v80/wu18g.html

[542]. Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions.

作者: Junru Wu,Yue Wang,Zhenyu Wu,Zhangyang Wang,Ashok Veeraraghavan,Yingyan Lin,

連結: http://proceedings.mlr.press/v80/wu18h.html

[543]. Bayesian Quadrature for Multiple Related Integrals.

作者: Xiaoyue Xi,François-Xavier Briol,Mark A. Girolami,

連結: http://proceedings.mlr.press/v80/xi18a.html

[544]. Model-Level Dual Learning.

作者: Yingce Xia,Xu Tan,Fei Tian,Tao Qin,Nenghai Yu,Tie-Yan Liu,

連結: http://proceedings.mlr.press/v80/xia18a.html

[545]. Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks.

作者: Lechao Xiao,Yasaman Bahri,Jascha Sohl-Dickstein,Samuel S. Schoenholz,Jeffrey Pennington,

連結: http://proceedings.mlr.press/v80/xiao18a.html

[546]. Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis.

作者: Pengtao Xie,Wei Wu,Yichen Zhu,Eric P. Xing,

連結: http://proceedings.mlr.press/v80/xie18a.html

[547]. Nonoverlap-Promoting Variable Selection.

作者: Pengtao Xie,Hongbao Zhang,Yichen Zhu,Eric P. Xing,

連結: http://proceedings.mlr.press/v80/xie18b.html

[548]. Learning Semantic Representations for Unsupervised Domain Adaptation.

作者: Shaoan Xie,Zibin Zheng,Liang Chen,Chuan Chen,

連結: http://proceedings.mlr.press/v80/xie18c.html

[549]. Rates of Convergence of Spectral Methods for Graphon Estimation.

作者: Jiaming Xu,

連結: http://proceedings.mlr.press/v80/xu18a.html

[550]. Learning Registered Point Processes from Idiosyncratic Observations.

作者: Hongteng Xu,Lawrence Carin,Hongyuan Zha,

連結: http://proceedings.mlr.press/v80/xu18b.html

[551]. Representation Learning on Graphs with Jumping Knowledge Networks.

作者: Keyulu Xu,Chengtao Li,Yonglong Tian,Tomohiro Sonobe,Ken-ichi Kawarabayashi,Stefanie Jegelka,

連結: http://proceedings.mlr.press/v80/xu18c.html

[552]. Learning to Explore via Meta-Policy Gradient.

作者: Tianbing Xu,Qiang Liu,Liang Zhao,Jian Peng,

連結: http://proceedings.mlr.press/v80/xu18d.html

[553]. Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information.

作者: Yichong Xu,Hariank Muthakana,Sivaraman Balakrishnan,Aarti Singh,Artur Dubrawski,

連結: http://proceedings.mlr.press/v80/xu18e.html

[554]. Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data.

作者: Ganggang Xu,Zuofeng Shang,Guang Cheng,

連結: http://proceedings.mlr.press/v80/xu18f.html

[555]. Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions.

作者: Pan Xu,Tianhao Wang,Quanquan Gu,

連結: http://proceedings.mlr.press/v80/xu18g.html

[556]. A Semantic Loss Function for Deep Learning with Symbolic Knowledge.

作者: Jingyi Xu,Zilu Zhang,Tal Friedman,Yitao Liang,Guy Van den Broeck,

連結: http://proceedings.mlr.press/v80/xu18h.html

[557]. Causal Bandits with Propagating Inference.

作者: Akihiro Yabe,Daisuke Hatano,Hanna Sumita,Shinji Ito,Naonori Kakimura,Takuro Fukunaga,Ken-ichi Kawarabayashi,

連結: http://proceedings.mlr.press/v80/yabe18a.html

[558]. Active Learning with Logged Data.

作者: Songbai Yan,Kamalika Chaudhuri,Tara Javidi,

連結: http://proceedings.mlr.press/v80/yan18a.html

[559]. Binary Classification with Karmic, Threshold-Quasi-Concave Metrics.

作者: Bowei Yan,Oluwasanmi Koyejo,Kai Zhong,Pradeep Ravikumar,

連結: http://proceedings.mlr.press/v80/yan18b.html

[560]. Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions.

作者: Karren D. Yang,Abigail Katoff,Caroline Uhler,

連結: http://proceedings.mlr.press/v80/yang18a.html

[561]. Dependent Relational Gamma Process Models for Longitudinal Networks.

作者: Sikun Yang,Heinz Koeppl,

連結: http://proceedings.mlr.press/v80/yang18b.html

[562]. Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy.

作者: Jiasen Yang,Qiang Liu,Vinayak A. Rao,Jennifer Neville,

連結: http://proceedings.mlr.press/v80/yang18c.html

[563]. Mean Field Multi-Agent Reinforcement Learning.

作者: Yaodong Yang,Rui Luo,Minne Li,Ming Zhou,Weinan Zhang,Jun Wang,

連結: http://proceedings.mlr.press/v80/yang18d.html

[564]. Yes, but Did It Work?: Evaluating Variational Inference.

作者: Yuling Yao,Aki Vehtari,Daniel Simpson,Andrew Gelman,

連結: http://proceedings.mlr.press/v80/yao18a.html

[565]. Hierarchical Text Generation and Planning for Strategic Dialogue.

作者: Denis Yarats,Mike Lewis,

連結: http://proceedings.mlr.press/v80/yarats18a.html

[566]. Communication-Computation Efficient Gradient Coding.

作者: Min Ye,Emmanuel Abbe,

連結: http://proceedings.mlr.press/v80/ye18a.html

[567]. Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach.

作者: Mao Ye,Yan Sun,

連結: http://proceedings.mlr.press/v80/ye18b.html

[568]. Loss Decomposition for Fast Learning in Large Output Spaces.

作者: Ian En-Hsu Yen,Satyen Kale,Felix X. Yu,Daniel Niels Holtmann-Rice,Sanjiv Kumar,Pradeep Ravikumar,

連結: http://proceedings.mlr.press/v80/yen18a.html

[569]. Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates.

作者: Dong Yin,Yudong Chen,Kannan Ramchandran,Peter L. Bartlett,

連結: http://proceedings.mlr.press/v80/yin18a.html

[570]. Semi-Implicit Variational Inference.

作者: Mingzhang Yin,Mingyuan Zhou,

連結: http://proceedings.mlr.press/v80/yin18b.html

[571]. Disentangled Sequential Autoencoder.

作者: Yingzhen Li,Stephan Mandt,

連結: http://proceedings.mlr.press/v80/yingzhen18a.html

[572]. Probably Approximately Metric-Fair Learning.

作者: Gal Yona,Guy N. Rothblum,

連結: http://proceedings.mlr.press/v80/yona18a.html

[573]. GAIN: Missing Data Imputation using Generative Adversarial Nets.

作者: Jinsung Yoon,James Jordon,Mihaela van der Schaar,

連結: http://proceedings.mlr.press/v80/yoon18a.html

[574]. RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks.

作者: Jinsung Yoon,James Jordon,Mihaela van der Schaar,

連結: http://proceedings.mlr.press/v80/yoon18b.html

[575]. GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models.

作者: Jiaxuan You,Rex Ying,Xiang Ren,William L. Hamilton,Jure Leskovec,

連結: http://proceedings.mlr.press/v80/you18a.html

[576]. An Efficient Semismooth Newton Based Algorithm for Convex Clustering.

作者: Yancheng Yuan,Defeng Sun,Kim-Chuan Toh,

連結: http://proceedings.mlr.press/v80/yuan18a.html

[577]. A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming.

作者: Alp Yurtsever,Olivier Fercoq,Francesco Locatello,Volkan Cevher,

連結: http://proceedings.mlr.press/v80/yurtsever18a.html

[578]. Orthogonal Machine Learning: Power and Limitations.

作者: Ilias Zadik,Lester W. Mackey,Vasilis Syrgkanis,

連結: http://proceedings.mlr.press/v80/zadik18a.html

[579]. Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs.

作者: Andrea Zanette,Emma Brunskill,

連結: http://proceedings.mlr.press/v80/zanette18a.html

[580]. Policy Optimization as Wasserstein Gradient Flows.

作者: Ruiyi Zhang,Changyou Chen,Chunyuan Li,Lawrence Carin,

連結: http://proceedings.mlr.press/v80/zhang18a.html

[581]. Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow.

作者: Xiao Zhang,Simon S. Du,Quanquan Gu,

連結: http://proceedings.mlr.press/v80/zhang18b.html

[582]. Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion.

作者: Richard Y. Zhang,Salar Fattahi,Somayeh Sojoudi,

連結: http://proceedings.mlr.press/v80/zhang18c.html

[583]. High Performance Zero-Memory Overhead Direct Convolutions.

作者: Jiyuan Zhang,Franz Franchetti,Tze Meng Low,

連結: http://proceedings.mlr.press/v80/zhang18d.html

[584]. Safe Element Screening for Submodular Function Minimization.

作者: Weizhong Zhang,Bin Hong,Lin Ma,Wei Liu,Tong Zhang,

連結: http://proceedings.mlr.press/v80/zhang18e.html

[585]. Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms.

作者: Xueru Zhang,Mohammad Mahdi Khalili,Mingyan Liu,

連結: http://proceedings.mlr.press/v80/zhang18f.html

[586]. Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization.

作者: Jiong Zhang,Qi Lei,Inderjit S. Dhillon,

連結: http://proceedings.mlr.press/v80/zhang18g.html

[587]. Learning Long Term Dependencies via Fourier Recurrent Units.

作者: Jiong Zhang,Yibo Lin,Zhao Song,Inderjit S. Dhillon,

連結: http://proceedings.mlr.press/v80/zhang18h.html

[588]. Tropical Geometry of Deep Neural Networks.

作者: Liwen Zhang,Gregory Naitzat,Lek-Heng Lim,

連結: http://proceedings.mlr.press/v80/zhang18i.html

[589]. Deep Bayesian Nonparametric Tracking.

作者: Aonan Zhang,John W. Paisley,

連結: http://proceedings.mlr.press/v80/zhang18j.html

[590]. Composable Planning with Attributes.

作者: Amy Zhang,Sainbayar Sukhbaatar,Adam Lerer,Arthur Szlam,Rob Fergus,

連結: http://proceedings.mlr.press/v80/zhang18k.html

[591]. Noisy Natural Gradient as Variational Inference.

作者: Guodong Zhang,Shengyang Sun,David Duvenaud,Roger B. Grosse,

連結: http://proceedings.mlr.press/v80/zhang18l.html

[592]. A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery.

作者: Xiao Zhang,Lingxiao Wang,Yaodong Yu,Quanquan Gu,

連結: http://proceedings.mlr.press/v80/zhang18m.html

[593]. Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents.

作者: Kaiqing Zhang,Zhuoran Yang,Han Liu,Tong Zhang,Tamer Basar,

連結: http://proceedings.mlr.press/v80/zhang18n.html

[594]. Dynamic Regret of Strongly Adaptive Methods.

作者: Lijun Zhang,Tianbao Yang,Rong Jin,Zhi-Hua Zhou,

連結: http://proceedings.mlr.press/v80/zhang18o.html

[595]. Inter and Intra Topic Structure Learning with Word Embeddings.

作者: He Zhao,Lan Du,Wray L. Buntine,Mingyuan Zhou,

連結: http://proceedings.mlr.press/v80/zhao18a.html

[596]. Adversarially Regularized Autoencoders.

作者: Junbo Jake Zhao,Yoon Kim,Kelly Zhang,Alexander M. Rush,Yann LeCun,

連結: http://proceedings.mlr.press/v80/zhao18b.html

[597]. MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning.

作者: Bo Zhao,Xinwei Sun,Yanwei Fu,Yuan Yao,Yizhou Wang,

連結: http://proceedings.mlr.press/v80/zhao18c.html

[598]. Composite Marginal Likelihood Methods for Random Utility Models.

作者: Zhibing Zhao,Lirong Xia,

連結: http://proceedings.mlr.press/v80/zhao18d.html

[599]. Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data.

作者: Shuai Zheng,James Tin-Yau Kwok,

連結: http://proceedings.mlr.press/v80/zheng18a.html

[600]. A Robust Approach to Sequential Information Theoretic Planning.

作者: Sue Zheng,Jason Pacheco,John W. Fisher III,

連結: http://proceedings.mlr.press/v80/zheng18b.html

[601]. Revealing Common Statistical Behaviors in Heterogeneous Populations.

作者: Andrey Zhitnikov,Rotem Mulayoff,Tomer Michaeli,

連結: http://proceedings.mlr.press/v80/zhitnikov18a.html

[602]. Understanding Generalization and Optimization Performance of Deep CNNs.

作者: Pan Zhou,Jiashi Feng,

連結: http://proceedings.mlr.press/v80/zhou18a.html

[603]. Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?

作者: Zhengyuan Zhou,Panayotis Mertikopoulos,Nicholas Bambos,Peter W. Glynn,Yinyu Ye,Li-Jia Li,Li Fei-Fei,

連結: http://proceedings.mlr.press/v80/zhou18b.html

[604]. A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates.

作者: Kaiwen Zhou,Fanhua Shang,James Cheng,

連結: http://proceedings.mlr.press/v80/zhou18c.html

[605]. Stochastic Variance-Reduced Cubic Regularized Newton Method.

作者: Dongruo Zhou,Pan Xu,Quanquan Gu,

連結: http://proceedings.mlr.press/v80/zhou18d.html

[606]. Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors.

作者: Yichi Zhou,Jun Zhu,Jingwei Zhuo,

連結: http://proceedings.mlr.press/v80/zhou18e.html

[607]. Distributed Nonparametric Regression under Communication Constraints.

作者: Yuancheng Zhu,John Lafferty,

連結: http://proceedings.mlr.press/v80/zhu18a.html

[608]. Message Passing Stein Variational Gradient Descent.

作者: Jingwei Zhuo,Chang Liu,Jiaxin Shi,Jun Zhu,Ning Chen,Bo Zhang,

連結: http://proceedings.mlr.press/v80/zhuo18a.html

[609]. Stochastic Variance-Reduced Hamilton Monte Carlo Methods.

作者: Difan Zou,Pan Xu,Quanquan Gu,

連結: http://proceedings.mlr.press/v80/zou18a.html

[610]. Hierarchical Long-term Video Prediction without Supervision.

作者: Nevan Wichers,Ruben Villegas,Dumitru Erhan,Honglak Lee,

連結: http://proceedings.mlr.press/v80/wichers18a.html