d78: ICML 2016 Accepted Papers

ICML 2016 Accepted Papers

• No Oops, You Won’t Do It Again: Mechanisms for Self-correction in Crowdsourcing ,Nihar Shah UC Berkeley, Dengyong Zhou Microsoft Research
• Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues ,Nihar Shah UC Berkeley, Sivaraman Balakrishnan CMU, Aditya Guntuboyina UC Berkeley, Martin Wainwright UC Berkeley
• Uprooting and Rerooting Graphical Models ,Adrian Weller University of Cambridge
• A Deep Learning Approach to Unsupervised Ensemble Learning ,Uri Shaham Yale University, Xiuyuan Cheng , Omer Dror , Ariel Jaffe , Boaz Nadler , Joseph Chang , Yuval Kluger
• Revisiting Semi-Supervised Learning with Graph Embeddings ,Zhilin Yang Carnegie Mellon University, Ruslan SalakhudinovU. of Toronto, William Cohen CMU
• Inverse Optimal Control with Deep Networks via Policy Optimization ,Chelsea Finn UC Berkeley, Sergey Levine , Pieter Abbeel Berkeley
• Diversity-Promoting Bayesian Learning of Latent Variable Models ,Pengtao Xie Carnegie Mellon University, Jun ZhuTsinghua, Eric Xing CMU
• Additive Approximations in High Dimensional Regression via the SALSA ,Kirthevasan Kandasamy Carnegie Mellon University, Yaoliang Yu
• Hawkes Processes with Stochastic Excitations ,Young Lee NICTA, Kar Wai Lim ANU, Cheng Soon Ong NICTA
• Data-driven Rank Breaking for Efficient Rank Aggregation ,Sewoong Oh UIUC, Ashish Khetan UIUC
• Dropout distillation ,Samuel Rota Bulò FBK, Lorenzo Porzi FBK, Peter Kontschieder Microsoft Research Cambridge
• Metadata-conscious anonymous messaging ,Giulia Fanti UIUC, Peter Kairouz UIUC, Sewoong Oh UIUC, Pramod ViswanathUIUC, kannan ramchandran
• The Teaching Dimension of Linear Learners ,Ji Liu University of Rochester, Xiaojin Zhu University of Wisconsin, Hrag Ohannessian University of Wisconsin-Madison
• Truthful Univariate Estimators ,Ioannis Caragiannis University of Patras, Ariel Procaccia Carnegie Mellon University, Nisarg Shah Carnegie Mellon University
• Why Regularized Auto-Encoders learn Sparse Representation? ,Devansh Arpit SUNY Buffalo, Yingbo Zhou SUNY Buffalo, Hung Ngo SUNY Buffalo, Venu Govindaraju SUNY Buffalo
• k-variates++: more pluses in the k-means++ ,Richard Nock Nicta & ANU, Raphael Canyasse Ecole Polytechnique and The Technion, Roksana Boreli Data61, Frank Nielsen Ecole Polytechnique and Sony CS Labs Inc.
• Multi-Player Bandits — a Musical Chairs Approach ,Jonathan Rosenski Weizmann Institute of Science, Ohad ShamirWeizmann Institute of Science, Liran Szlak Weizmann Institute of Science
• The Information Sieve ,Greg Ver Steeg Information Sciences Institute, Aram Galstyan Information Sciences Institute
• End-to-End Speech Recognition in English and Mandarin ,Sanjeev Satheesh Baidu SVAIL, Dario Amodei , Rishita Anubhai , Eric Battenberg , Carl Case , Jared Casper , Bryan Catanzaro , Mike Chrzanowski Baidu USA, Adam Coates , Greg Diamos Baidu USA, Erich Elsen Baidu USA, Jesse Engel , Christopher Fougner , Awni Hannun Baidu USA, Billy Jun , Patrick LeGresley , Sharan Narang , Andrew Ng , Sherjil Ozair , Ryan Prenger , Jonathan Raiman , David Seetapun , Shubho Sengupta , Chong Wang , Yi Wang , Libby Lin , Tony Han , zhenyao Zhu , Dani Yogatama , Bo Xiao , JingDong Chen , Zhiqian Wang , Jun Zhan , Linxi Fan
• On the Consistency of Feature Selection With Lasso for Non-linear Targets ,Yue Zhang Case Western Reserve University, Weihong Guo Case Western Reserve University, Soumya Ray
• Minimum Regret Search for Single- and Multi-Task Optimization ,Jan Hendrik Metzen University Bremen
• CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy ,Nathan Dowlin Princeton, Ran , Kim Laine Microsoft Research, Kristin Lauter Microsoft Research, Michael Naehrig Microsoft Research, John WernsingMicrosoft Research
• The Variational Nystrom method for large-scale spectral problems ,Max Vladymyrov Yahoo Labs, Miguel Carreira-PerpinanUC Merced
• MBA: Multi-Bias Non-linear Activation in Deep Neural Networks ,Hongyang Li The Chinese Univ. of HK, Wanli Ouyang , Xiaogang Wang
• Asymmetric Multi-task Learning based on Task Relatedness and Confidence ,Giwoong Lee UNIST, Eunho Yang IBM Research, Sung ju Hwang UNIST
• Accurate Robust and Efficient Error Estimation for Decision Trees ,Lixin Fan Nokia Technologies
• Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity ,Ohad Shamir Weizmann Institute of Science
• Convergence of Stochastic Gradient Descent for PCA ,Ohad Shamir Weizmann Institute of Science
• Dealbreaker: A Nonlinear Latent Variable Model for Educational Data ,Andrew Lan Rice University, Tom Goldstein University of Maryland, Christoph Studer Cornell University, Richard Baraniuk Rice University
• A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation ,qiang liu , Jason Lee UC Berkeley, Michael
• Variable Elimination in the Fourier Domain ,Yexiang Xue Cornell University, Stefano Ermon , Ronan Le Bras Cornell University, Carla , Bart
• Low-Rank Matrix Approximation with Stability ,Dongsheng Li IBM Research – China, Chao Chen , Qin Lv , Junchi Yan , Li Shang , Stephen Chu
• Linking losses for density ratio and class-probability estimation ,Aditya Menon National ICT Australia, Cheng Soon OngNICTA
• Stochastic Variance Reduction for Nonconvex Optimization ,Sashank J. Reddi Carnegie Mellon University, Ahmed Hefny , Suvrit Sra , Barnabas Poczos , Alex
• Hierarchical Variational Models ,Rajesh Ranganath , Dustin Tran Columbia University, Blei David Columbia
• Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams ,Roy Adams Univ. of Massachusetts-Amherst, Nazir Saleheen , Edison Thomaz , Abhinav Parate , Santosh Kumar , Ben Marlin
• Binary embeddings with structured hashed projections ,Anna Choromanska Courant Institute, Krzysztof Choromanski Google Research NYC, Mariusz Bojarski NVIDIA, Tony Jebara Columbia, Sanjiv Kumar , Yann
• A Variational Analysis of Stochastic Gradient Algorithms ,Stephan Mandt Columbia University, Matthew Hoffman Adobe Research, Blei David Columbia
• Adaptive Sampling for SGD by Exploiting Side Information ,Siddharth Gopal
• Learning from Multiway Data: Simple and Efficient Tensor Regression ,Rose Yu University of Southern Cal, Yan Liu
• A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression Models ,Trong Nghia Hoang NUS, Quang Minh Hoang NUS, Bryan Kian Hsiang Low NUS
• Online Stochastic Linear Optimization under One-bit Feedback ,Lijun Zhang Nanjing University, Tianbao Yang University of Iowa, Rong Jin Alibaba Group, Yichi Xiao Nanjing University, Zhi-hua Zhou
• Adaptive Algorithms for Online Convex Optimization with Long-term Constraints ,Rodolphe Jenatton , Jim Huang Amazon, Cedric Archambeau
• Actively Learning Hemimetrics with Applications to Eliciting User Preferences ,Adish Singla , Sebastian Tschiatschek ETH Zurich, Andreas Krause
• Learning Simple Algorithms from Examples ,Wojciech Zaremba , Tomas , Armand Joulin , Rob Fergus Facebook AI Research
• Learning Physical Intuition of Block Towers by Example ,Adam Lerer Facebook AI Research, Rob Fergus Facebook AI Research
• Structure Learning of Partitioned Markov Networks ,Song Liu The Inst. of Stats. Math., Taiji Suzuki , Masashi SugiyamaUniversity of Tokyo, Kenji
• Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient ,Tianbao Yang University of Iowa, Lijun Zhang Nanjing University, Rong Jin , Jinfeng Yi IBM Research
• Beyond CCA: Moment Matching for Multi-View Models ,Anastasia Podosinnikova INRIA – ENS, Francis Bach Inria, Simon Lacoste-Julien INRIA
• Fast Methods for Estimating the Numerical Rank of Large Matrices ,Shashanka Ubaru University of Minnesota, Yousef SaadUniversity of Minnesota
• Unsupervised Deep Embedding for Clustering Analysis ,Junyuan Xie University of Washington, Ross Girshick Facebook, Ali Farhadi University of Washington
• Efficient Private Empirical Risk Minimization for High-dimensional Learning ,Shiva Kasiviswanathan Samsung Research America, Hongxia Jin Samsung Research America
• Parameter Estimation for Generalized Thurstone Choice Models ,Milan Vojnovic Microsoft, Seyoung Yun Microsoft
• Large-Margin Softmax Loss for Convolutional Neural Networks ,Weiyang Liu Peking University, Yandong Wen South China University of Technology, Zhiding Yu Carnegie Mellon University, Meng Yang Shenzhen University
• A Random Matrix Approach to Recurrent Neural Networks ,Romain Couillet CentraleSupelec, Gilles Wainrib ENS Ulm, Hafiz Tiomoko Ali CentraleSupelec, Harry Sevi ENS Lyon
• Supervised and Semi-Supervised Text Categorization using One-Hot LSTM for Region Embeddings ,Rie Johnson RJ Research Consulting, Tong Zhang
• Optimality of Belief Propagation for Crowdsourced Classification ,Jungseul Ok KAIST, Sewoong Oh UIUC, Jinwoo ShinKAIST, Yung Yi KAIST
• Stability of Controllers for Gaussian Process Forward Models ,Julia Vinogradska Robert Bosch GmBH, Bastian Bischoff , Duy Nguyen-Tuong , Anne Romer , Henner Schmidt , Jan Peters
• Learning privately from multiparty data ,Jihun Hamm , Yingjun Cao UC-San Diego, Mikhail Belkin
• Network Morphism ,Tao Wei University at Buffalo, Changhu Wang Microsoft Research, Yong Rui Microsoft Research, Chang Wen Chen
• A Kronecker-factored approximate Fisher matrix for convolution layers ,Roger Grosse , James Martens University of Toronto
• Experimental Design on a Budget for Sparse Linear Models and Applications ,Sathya Narayanan Ravi UW Madison, Vamsi Ithapu UW Madison, Vikas Singh , Sterling Johnson UW Madison
• Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVM ,Anton Osokin , Jean-Baptiste Alayrac ENS, Puneet Dokania INRIA and Ecole Centrale Paris, Simon Lacoste-Julien INRIA
• Exact Exponent in Optimal Rates for Crowdsourcing ,Chao Gao Yale University, Yu Lu Yale University, Dengyong ZhouMicrosoft Research
• Augmenting Neural Networks with Reconstructive Decoding Pathways for Large-scale Image Classification ,Yuting ZhangUniversity of Michigan, Kibok Lee University of Michigan, Honglak Lee University of Michigan
• Online Low-Rank Subspace Clustering by Explicit Basis Modeling ,Jie Shen Rutgers University, Ping Li Rutgers, Huan Xu
• A Self-Correcting Variable-Metric Algorithm for Stochastic Optimization ,Frank Curtis Lehigh University
• Stochastic Quasi-Newton Langevin Monte Carlo ,Umut Simsekli Telecom ParisTech, Roland Badeau , Taylan Cemgil , Gaël Richard
• Doubly Robust Off-policy Value Evaluation for Reinforcement Learning ,Nan Jiang University of Michigan, Lihong Li Microsoft
• Fast Rate Analysis of Some Stochastic Optimization Algorithms ,Chao Qu Nus, Huan Xu , Chong jin Ong Nus
• Fast k-Nearest Neighbour Search via Dynamic Continuous Indexing ,Ke Li UC Berkeley, Jitendra Malik
• Smooth Imitation Learning ,Hoang Le Caltech, Andrew Kang , Yisong Yue Caltech, Peter Carr
• Community Recovery in Graphs with Locality ,Yuxin Chen Stanford University, Govinda Kamath Stanford University, Changho Suh KAIST, David Tse Stanford University
• Variance Reduction for Faster Non-Convex Optimization ,Zeyuan Allen-Zhu Princeton University, Elad Hazan Princeton University
• Loss factorization, weakly supervised learning and label noise robustness ,Giorgio Patrini ANU / Data61, Frank NielsenEcole Polytechnique and Sony CS Labs Inc., Richard Nock Nicta & ANU, Marcello Carioni Max Planck Institute
• Analysis of Deep Neural Networks with Extended Data Jacobian Matrix ,Shengjie Wang University of Washington, Abdel-rahman Mohamed , Rich Caruana Microsoft, Jeff Bilmes U. of Washington, Matthai Plilipose , Matthew Richardson , Krzysztof Geras , Gregor Urban UC Irvine, Ozlem Aslan
• Doubly Decomposing Nonparametric Tensor Regression ,Masaaki Imaizumi University of Tokyo, Kohei Hayashi NII
• Hyperparameter optimization with approximate gradient ,Fabian Pedregosa INRIA
• SDCA without Duality, Regularization, and Individual Convexity ,Shai Shalev-Shwartz Hebrew University of Jerusalem
• Heteroscedastic Sequences: Beyond Gaussianity ,Oren , Shie Mannor Technion
• A Neural Autoregressive Approach to Collaborative Filtering ,Yin Zheng Hulu LLC., Bangsheng Tang Hulu LLC, Wenkui DingHulu LLC., Hanning Zhou Hulu
• On the Quality of the Initial Basin in Overspecified Neural Networks ,Itay Safran Weizmann Institute of Science, Ohad ShamirWeizmann Institute of Science
• Primal-Dual Rates and Certificates ,Celestine Dünner IBM Research, Simone Forte Google, Martin Takac , Martin Jaggi
• Minimizing the Maximal Loss: How and Why ,Shai Shalev-Shwartz Hebrew University of Jerusalem, Yonatan Wexler Orcam
• The Sample Complexity of Subspace Clustering with Missing Data ,Daniel Pimentel-Alarcon UW-Madison, Robert Nowak
• Online Learning with Feedback Graphs Without the Graphs ,Alon Cohen Technion, Tamir Hazan , Tomer Koren
• PAC learning of Probabilistic Automaton based on the Method of Moments ,Hadrien Glaude University of Lille, Olivier Pietquin Univ. Lille
• Estimating Structured Vector Autoregressive Models ,Igor Melnyk University of Minnesota, Arindam Banerjee
• Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends ,Christopher Tosh UC San Diego
• Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms ,Mathieu Blondel NTT, Masakazu Ishihata NTT Communication Science Labo, Akinori Fujino NTT, Naonori Ueda
• A New PAC-Bayesian Perspective on Domain Adaptation ,Pascal Germain INRIA, Amaury Habrard , François LavioletteGRAAL, Emilie Morvant
• Correlation Clustering and Biclustering with Locally Bounded Errors ,Gregory Puleo UIUC, Olgica Milenkovic UIUC
• PAC Lower Bounds and Efficient Algorithms for The Max KK-Armed Bandit Problem ,Yahel David Technion, Nahum ShimkinTechnion
• A Comparative Analysis and Study of Multiview Convolutional Neural Network Models for Joint Object Categorization and Pose Estimation ,Mohamed Elhoseiny Rutgers University, Tarek El-Gaaly Rutgers University, Amr Bakry Rutgers University, Ahmed Elgammal Rutgers University
• BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces ,Shane CarrWashington University in St. L, Roman Garnett Wustl, Cynthia Lo Washington University in St. Louis
• On the Iteration Complexity of Oblivious First-Order Optimization Algorithms ,Yossi Arjevani Weizmann Institute of Science, Ohad Shamir Weizmann Institute of Science
• Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning ,Xingguo Li University of Minnesota, Tuo Zhao , Raman Arora Johns Hopkins University, Han , Jarvis Haupt
• Analysis of Variational Bayesian Factorizations for Sparse and Low-Rank Estimation ,David Wipf Microsoft Research
• Fast k-means with accurate bounds ,James Newling Idiap Research Institute, Francois Fleuret Idiap research institute
• Boolean Matrix Factorization and Noisy Completion via Message Passing ,Siamak Ravanbakhsh CMU, Barnabas Poczos , Russell Greiner University of Alberta
• Convolutional Rectifier Networks as Generalized Tensor Decompositions ,Nadav Cohen Hebrew University of Jerusalem, Amnon Shashua Mobileye
• Low-rank Solutions of Linear Matrix Equations via Procrustes Flow ,Stephen Tu UC Berkeley, Ross Boczar UC Berkeley, Max Simchowitz UC Berkeley, mahdi Soltanolkotabi , Ben Recht Berkeley
• Anytime Exploration for Multi-armed Bandits using Confidence Information ,Kwang-Sung Jun UW-Madison, Robert Nowak
• Structured Prediction Energy Networks ,David Belanger University of Massachusetts Am, Andrew McCallum
• L1-regularized Neural Networks are Improperly Learnable in Polynomial Time ,Yuchen Zhang , Jason Lee UC Berkeley, Michael
• Compressive Spectral Clustering ,Nicolas TREMBLAY INRIA Rennes, Gilles Puy INRIA, Remi Gribonval INRIA, Pierre Vandergheynst EPFL
• Low-rank tensor completion: a Riemannian manifold preconditioning approach , Hiroyuki Kasai The University of Electro-Comm, Bamdev Mishra Amazon Development Centre India
• Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow ,Huishuai Zhang Syracuse University, Yuejie Chi Ohio State University, Yingbin Liang Syracuse University
• Estimating Maximum Expected Value through Gaussian Approximation ,Carlo D’Eramo Politecnico di Milano, Marcello Restelli Politecnico di Milano, Alessandro Nuara Politecnico di Milano
• Representational Similarity Learning with Application to Brain Networks ,Urvashi Oswal University of Wisconsin, Christopher Cox University of Wisconsin, Timothy Rogers University of Wisconsin, Robert Nowak
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning ,Yarin Gal University of Cambridge, Zoubin
• Generative Adversarial Text to Image Synthesis ,Scott Reed , Zeynep Akata Max Planck Institute for Informatics, Xinchen YanUniversity of Michigan, Lajanugen Logeswaran University of Michigan – Ann Arbor, Honglak Lee University of Michigan, Bernt Schiele
• Dirichlet Process Mixture Model for Correcting Technical Variation in Single-Cell Gene Expression Data ,Sandhya Prabhakaran Columbia University, Elham Azizi Columbia University, Ambrose Carr Columbia University, Dana Pe’er Columbia University
• Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives ,Zeyuan Allen-Zhu Princeton University, Yang Yuan Cornell
• Sparse Parameter Recovery from Aggregated Data ,Avradeep Bhowmik University of Texas at Austin, Joydeep , Oluwasanmi Koyejo Stanford University & University of Illinois at Urbana Champaign
• Deep Structured Energy Based Models for Anomaly Detection ,Shuangfei Zhai Binghamton University, Yu Cheng IBM Research, Zhongfei Zhang Binghamton University
• Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling ,Zeyuan Allen-Zhu Princeton University, Zheng Qu The University of Hong Kong, Peter Richtarik , Yang Yuan Cornell
• Unitary Evolution Recurrent Neural Networks ,Martin Arjovsky University of Buenos Aires, Amar Shah University of Cambridge, Yoshua Bengio
• Markov Latent Feature Models ,Aonan Zhang Columbia University, John Paisley
• The Knowledge Gradient for Sequential Decision Making with Stochastic Binary Feedbacks ,Yingfei Wang Princeton University, Chu Wang , Warren Powell
• A Simple and Provable Algorithm for Sparse CCA ,Megasthenis Asteris University of Texas at Austin, Anastasios Kyrillidis , Oluwasanmi Koyejo Stanford University & University of Illinois at Urbana Champaign, Russell Poldrack Stanford University
• Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods ,Huikang Liu CUHK, Weijie Wu CUHK, Anthony Man-Cho So
• Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks ,Devansh Arpit SUNY Buffalo, Yingbo Zhou SUNY Buffalo, Bhargava Kota SUNY Buffalo, Venu Govindaraju SUNY Buffalo
• Learning to Generate with Memory ,Chongxuan Li Tsinghua University, Jun Zhu Tsinghua, Bo Zhang Tsinghua University
• Learning End-to-end Video Classification with Rank-Pooling ,Basura Fernando ANU Canberra Australia, Stephen GouldAustralian National University
• Learning to Filter with Predictive State Inference Machines ,Wen Sun Carnegie Mellon University, Arun Venkatraman Carnegie Mellon University, Byron Boots , J.Andrew Bagnell Carnegie Mellon University
• A Subspace Learning Approach for High Dimensional Matrix Decomposition with Efficient Column/Row Sampling,Mostafa Rahmani University of Central Florida, Geroge Atia University of Central Florida
• DCM Bandits: Learning to Rank with Multiple Clicks ,Sumeet Katariya University of Wisconsin Madiso, Branislav Kveton , Csaba Szepesvari Alberta, Zheng Wen Adobe Research
• Train faster, generalize better: Stability of stochastic gradient descent ,Moritz Hardt Google, Ben Recht Berkeley, Yoram
• Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm,Junpei Komiyama The University of Tokyo, Junya Honda The University of Tokyo, Hiroshi Nakagawa The University of Tokyo
• Contextual Combinatorial Cascading Bandits ,Shuai Li CUHK, Baoxiang Wang , Shengyu Zhang , Wei Chen
• Conservative Bandits ,Roshan Shariff University of Alberta, Yifan Wu , Tor , Csaba Szepesvari Alberta
• Variance-Reduced and Projection-Free Stochastic Optimization ,Elad Hazan Princeton University, Haipeng Luo
• Factored Temporal Sigmoid Belief Networks for Sequence Learning ,Jiaming Song Tsinghua University, Zhe Gan Duke University, Lawrence Carin
• False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking ,QianQian XuIIE, Jiechao Xiong Peking University, Xiaochun Cao Institute of information engineering, Yuan Yao Peking University
• Strongly-Typed Recurrent Neural Networks ,David Balduzzi , Muhammad Ghifary Victoria University Wellington, Weta DigitalNA
• Distributed Clustering of Linear Bandits in Peer to Peer Networks ,Nathan Korda University of Oxford, Balazs Szorenyi , Shuai Li University of Insubria
• Collapsed Variational Inference for Sum-Product Networks ,Han Zhao Carnegie Mellon University, Tameem Adel University of Amsterdam, Geoff Gordon CMU, Brandon Amos Carnegie Mellon University
• On the Analysis of Complex Backup Strategies in Monte Carlo Tree Search ,Piyush Khandelwal University of Texas at Austin, Elad Liebman , Scott , Peter Stone U. of Texas
• Benchmarking Deep Reinforcement Learning for Continuous Control ,Yan Duan University of California, Xi Chen University of California, Rein Houthooft Ghent University, John Schulman University of California, Pieter Abbeel Berkeley
• KK-Means Clustering with Distributed Dimensions ,Hu Ding State University of New York at Buffalo, Lingxiao Huang , Yu LiuTsinghua University, Jian Li
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images ,Dmity Ulyanov Skolkovo institute of science , Vadim Lebedev , Andrea , Victor Lempitsky Skolkovo Institute of Sci&Tech
• Fast Constrained Submodular Maximization: Personalized Data Summarization ,Baharan Mirzasoleiman ETH Zurich, Ashwinkumar Badanidiyuru Google Research, Amin Karbasi Yale University
• On the Statistical Limits of Convex Relaxations ,Zhaoran Wang Princeton University, Quanquan Gu , Han
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing ,Ankit Kumar MetaMind, Ozan IrsoyMetaMind, Mohit Iyyer MetaMind, James Bradbury MetaMind, Ishaan Gulrajani MetaMind, Victor Zhong MetaMind, Romain PaulusMetaMind, Richard Socher
• Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions ,Igor Colin , Aurelien Bellet INRIA, Joseph Salmon , Stéphan Clémençon
• Solving Ridge Regression using Sketched Preconditioned SVRG ,Alon , Francesco Orabona Yahoo, Shai Shalev-ShwartzHebrew University of Jerusalem
• Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control ,Prashanth L.A. University of Maryland , Cheng Jie University of Maryland – College Park, Michael Fu University of Maryland – College Park, Steve Marcus University of Maryland – College Park, Csaba Szepesvari Alberta
• Estimating Accuracy from Unlabeled Data: A Bayesian Approach ,Emmanouil Antonios Platanios Carnegie Mellon University, Avinava Dubey Carnegie Mellon University, Tom Mitchell Carnegie Mellon University
• Non-negative Matrix Factorization under Heavy Noise ,Jagdeep Pani Indian Institute of Science, Ravindran Kannan Microsoft Reseach India, Chiranjib Bhattacharya , Navin Goyal Microsoft Research India
• Extreme F-measure Maximization using Sparse Probability Estimates ,Kalina Jasinska , Krzysztof Dembczynski , Robert Busa-Fekete , Karlson Pfannschmidt , Timo Klerx , Eyke Hullermeier
• Auxiliary Deep Generative Models ,Lars Maaløe Technical University Denmark, Casper Kaae Sønderby University of Copenhagen, Søren Kaae Sønderby University of Copenagen, Ole Winther Technical University of Denmark
• Importance Sampling Tree for Large-scale Empirical Expectation ,Olivier CANEVET Idiap Research Institut, Cijo Jose Idiap Research Institute/ Éc , Francois Fleuret Idiap research institute
• Starting Small – Learning with Adaptive Sample Sizes ,Hadi Daneshmand ETH Zurich, Aurelien Lucchi ETHZ, Thomas Hofmann
• Deep Gaussian Processes for Regression using Approximate Expectation Propagation ,Thang Bui University of Cambridge, Daniel Hernandez-Lobato , Yingzhen Li University of Cambridge, Jose miguel Hernandez-Lobato , Richard Turner University of Cambridge
• DR-ABC: Approximate Bayesian Computation with Kernel-Based Distribution Regression ,Jovana Mitrovic University of Oxford, Dino Sejdinovic University of Oxford, Yee-Whye Teh Oxford
• Predictive Entropy Search for Multi-objective Bayesian Optimization ,Daniel Hernandez-Lobato , Jose miguel Hernandez-Lobato , Amar Shah University of Cambridge, Ryan Adams Harvard
• Rich Component Analysis ,Rong Ge , James Zou
• Black-Box Alpha Divergence Minimization ,Jose miguel Hernandez-Lobato , Yingzhen Li University of Cambridge, Mark Rowland University of Cambridge, Thang Bui University of Cambridge, Daniel Hernandez-Lobato , Richard Turner University of Cambridge
• One-Shot Generalization in Deep Generative Models ,Danilo Rezende Google DeepMind, Shakir , Daan Wierstra Google DeepMind
• Optimal Classification with Multivariate Losses ,Nagarajan Natarajan Microsoft Research India, Oluwasanmi Koyejo Stanford University & University of Illinois at Urbana Champaign, Pradeep Ravikumar UT Austin, Inderjit
• A ranking approach to global optimization ,Cedric Malherbe ENS Cachan, Emile Contal ENS Cachan, Nicolas Vayatis ENS Cachan
• Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms ,Yu-Xiang Wang , Veeranjaneyulu Sadhanala , Wei DaiCarnegie Mellon University, Willie Neiswanger , Suvrit Sra , Eric Xing CMU
• Autoencoding beyond pixels using a learned similarity metric ,Anders B. L. Larsen Technical University of Denmar, Søren Kaae Sønderby University of Copenagen, Hugo Larochelle Twitter, Ole Winther Technical University of Denmark
• Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling ,Christopher De Sa Stanford, Chris Re Stanford University, Kunle Olukotun Stanford
• Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling ,Atsushi Shibagaki Nagoya Institute of Technology, Masayuki Karasuyama Nagoya Institute of Technology, Kohei Hatano Kyushu University, Ichiro Takeuchi
• Anytime optimal algorithms in stochastic multi-armed bandits ,Rémy Degenne Université Paris Diderot, Vianney Perchet
• Bounded Off-Policy Evaluation with Missing Data for Course Recommendation and Curriculum Design ,William HoilesUCLA, Mihaela van der Schaar
• Mixed membership modelling with hierarchical CRMs ,Gaurav Pandey Indian Institute of Science, Ambedkar Dukkipati Indian Institute of Science
• From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification ,Andre Martins , Ramon AstudilloUnbabel
• Black-box optimization with a politician ,Sebastien Bubeck Microsoft, Yin Tat Lee MIT
• Gaussian process nonparametric tensor estimator and its minimax optimality ,Heishiro Kanagawa Tokyo Institute of Technology, Taiji Suzuki , Hayato Kobayashi Yahoo Japan Corporation, Nobuyuki Shimizu , Yukihiro Tagami Yahoo Japan Corporation
• No-Regret Algorithms for Heavy-Tailed Linear Bandits ,Andres Munoz Medina , Scott Yang
• Extended and Unscented Kitchen Sinks ,Edwin Bonilla UNSW, Daniel Steinberg DATA61, Alistair Reid Data61
• Matrix Eigendecomposition via Doubly Stochastic Riemannian Optimization ,Zhiqiang Xu Institute of Infocomm Research, Peilin Zhao I2R
• Recommendations as Treatments: Debiasing Learning and Evaluation ,Tobias Schnabel Cornell University, Thorsten Joachims Cornell, Adith Swaminathan Cornell University, Ashudeep Singh Cornell University, Navin Chandak Google
• ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission ,Jinsung YoonUniversity of California, Ahmed Alaa University of California, Scott Hu University of California, Mihaela van der Schaar
• An optimal algorithm for the Thresholding Bandit Problem ,Andrea LOCATELLI University of Potsdam, Maurilio GutzeitUniversität Potsdam, Alexandra Carpentier
• Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching ,Mu Niu University of Glasgow, Simon Rogers University of Glasgow, Maurizio Filippone EURECOM, Dirk Husmeier University of Glasgow
• The Deep Neural Matrix Gaussian Process ,Christos Louizos University of Amsterdam, Max Welling University of Amsterdam / CIFAR
• Learning Granger Causality for Hawkes Processes ,Hongteng Xu Georgia Tech, Mehrdad Farajtabar , Hongyuan
• Neural Variational Inference for Text Processing ,Yishu Miao University of Oxford, Lei Yu University of Oxford, Phil Blunsom
• Dictionary Learning for Massive Matrix Factorization ,Arthur Mensch Inria, Julien Mairal , Bertrand Thirion Inria, Gael Varoquaux
• Pixel Recurrent Neural Networks ,Aaron Van den Oord Google Deepmind, Nal Kalchbrenner Google Deepmind, Koray Kavukcuoglu Google Deepmind
• Sequential decision making under uncertainty: Are most decisions easy? ,Ozgur Simsek , Simon Algorta , Amit Kothiyal
• Gaussian quadrature for matrix inverse forms with applications ,Chengtao Li MIT, Suvrit Sra , Stefanie Jegelka MIT
• Train and Test Tightness of LP Relaxations in Structured Prediction ,Ofer Meshi , Mehrdad Mahdavi , Adrian Weller University of Cambridge, David Sontag NYU
• Stochastic Optimization for Multiview Learning using Partial Least Squares ,Raman Arora Johns Hopkins University, Poorya Mianjy Johns Hopkins University, Teodor Marinov
• Hierarchical Compound Poisson Factorization ,Mehmet Basbug Princeton University, Barbara Engelhardt
• Opponent Modeling in Deep Reinforcement Learning ,He He , Jordan , Hal Daume Maryland
• No penalty no tears: Least squares in high-dimensional linear models ,Xiangyu Wang Duke University, David , Chenlei LengUniversity of Warwick
• SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization ,Zheng Qu University of Hong Kong, Peter Richtarik , Martin Takac , Olivier Fercoq LTCI
• On Graduated Optimization for Stochastic Non-Convex Problems ,Elad Hazan Princeton University, Kfir Yehuda LevyTechnion, Shai Shalev-Shwartz Hebrew University of Jerusalem
• Meta-Learning with Memory-Augmented Neural Networks ,Adam Santoro Google DeepMind, Sergey Bartunov Higher School of Economics, Matthew Botvinick , Daan Wierstra Google DeepMind, Timothy Lillicrap Google DeepMind
• The knockoff filter for FDR control in group-sparse and multitask regression ,Ran Dai The University of Chicago, Rina Barber The University of Chicago
• Softened Approximate Policy Iteration for Markov Games ,Julien Pérolat Univ. Lille, Bilal Piot Univ. Lille, Matthieu Geist , Bruno Scherrer , Olivier Pietquin Univ. Lille
• Stochastic Block BFGS: Squeezing More Curvature out of Data ,Robert Gower University of Edinburgh, Donald GoldfarbColumbia University, Peter Richtarik
• Class Probability Estimation via Differential Geometric Regularization ,Qinxun Bai Boston University, Steven RosenbergBoston University, Zheng Wu The Mathwork Inc., Stan Sclaroff Boston University
• Exploiting Cyclic Symmetry in Convolutional Neural Networks ,Sander Dieleman Google DeepMind, Jeffrey De Fauw Google DeepMind, Koray Kavukcuoglu Google Deepmind
• Graying the black box: Understanding DQNs ,Tom Zahavy Technion, Nir Ben-Zrihem , Shie Mannor Technion
• The Sum-Product Theorem: A Foundation for Learning Tractable Models ,Abram Friesen University of Washington, Pedro
• Pareto Frontier Learning with Expensive Correlated Objectives ,Amar Shah University of Cambridge, Zoubin
• Asynchronous Methods for Deep Reinforcement Learning ,Volodymyr Mnih Google DeepMind, Adria Puigdomenech BadiaGoogle DeepMind, Mehdi Mirza , Alex Graves Google DeepMind, Timothy Lillicrap Google DeepMind, Tim Harley Google DeepMind, David , Koray Kavukcuoglu Google Deepmind
• A Simple and Strongly-Local Flow-Based Method for Cut Improvement ,Luke Veldt Purdue Unversity, David Gleich Purdue University, Michael
• Nonlinear Statistical Learning with Truncated Gaussian Graphical Models ,Qinliang Su Duke University, xuejun Liao , changyou Chen , Lawrence Carin
• Barron and Covers’ Theory in Supervised Learning　and Its Application to Lasso ,Masanori Kawakita Kyushu University, Jun’ichi Takeuchi Kyushu University
• Nonparametric canonical correlation analysis ,Tomer Michaeli Technion, Weiran Wang , Karen Livescu TTI Chicago
• BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits ,Alexander , Karthik Sridharan Yahoo
• Associative Long Short-Term Memory ,Ivo Danihelka Google DeepMind, Greg Wayne Google DeepMind, Benigno Uria Google DeepMind, Nal Kalchbrenner Google Deepmind, Alex Graves Google DeepMind
• Dueling Network Architectures for Deep Reinforcement Learning ,Ziyu Wang Google Inc., Nando de Freitas University of Oxford, Tom Schaul Google Inc., Matteo Hessel Google Deepmind, Hado van Hasselt Google DeepMind, Marc Lanctot Google Deepmind
• Persistence weighted Gaussian kernel for topological data analysis ,Genki Kusano Tohoku University, Yasuaki Hiraoka , Kenji
• Learning Convolutional Neural Networks for Graphs ,Mathias Niepert NEC Laboratories Europe, Mohamed Ahmed NEC Laboratories Europe, Konstantin Kutzkov NEC Laboratories Europe
• Persistent RNNs: Stashing Recurrent Weights On-Chip ,Greg Diamos Baidu USA, Shubho Sengupta Baidu USA, Bryan Catanzaro Baidu USA, Mike Chrzanowski Baidu USA, Adam Coates , Erich Elsen Baidu USA, Jesse Engel Baidu USA, Awni Hannun Baidu USA, Sanjeev Satheesh Baidu USA
• Recurrent Orthogonal Networks and Long-Memory Tasks ,Mikael Henaff NYU, Arthur , Yann
• The Arrow of Time in Multivariate Time Series ,Stefan Bauer ETH Zurich, Bernhard Schölkopf , Jonas
• Mixture Proportion Estimation via Kernel Embeddings of Distributions ,Harish Ramaswamy , Clayton , Ambuj
• Fast DPP Sampling for Nystrom with Application to Kernel Methods ,Chengtao Li MIT, Stefanie Jegelka MIT, Suvrit Sra
• Complex Embeddings for Simple Link Prediction ,Théo Trouillon Xerox, Johannes Welbl , Guillaume Bouchard , Sebastian Riedel , Eric Gaussier
• Interactive Bayesian Hierarchical Clustering ,Sharad Vikram UCSD, Sanjoy Dasgupta UCSD
• A Convolutional Attention Network for Extreme Summarization of Source Code ,Miltiadis Allamanis University of Edinburgh, Hao Peng Peking University, Charles
• How to Fake Multiply by a Gaussian Matrix ,Vamsi Potluru Comcast Cable, Michael Kapralov , David Woodruff
• Differentially Private Chi-Squared Hypothesis Testing: Goodness of Fit and Independence Testing ,Ryan Rogers University of Pennsylvania, Salil Vadhan Harvard University, Hyun Lim UCLA, Marco Gaboardi University at Buffalo
• Pliable Rejection Sampling ,Akram Erraqabi Inria Lille Nord Europe, Michal Valko Inria Lille – Nord Europe, Alexandra Carpentier, Odalric Maillard Inria
• Differentially Private Policy Evaluation ,Borja Balle Lancaster University, Maziar Gomrokchi McGill University, Doina PrecupMcGill
• Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning ,Philip Thomas CMU, Emma
• Discrete Deep Feature Extraction: A Theory and New Architectures ,Thomas Wiatowski ETH Zurich, Michael Tschannen ETH Zurich, Aleksandar Stanic ETH Zurich, Philipp Grohs University of Vienna, Helmut Boelcskei ETH Zurich
• Efficient Algorithms for Adversarial Contextual Learning ,Vasilis Syrgkanis Microsoft Research, Akshay KrishnamurthyMicrosoft Research, Robert Schapire Microsoft Research
• Training Deep Neural Networks via Direct Loss Minimization ,Yang Song Tsinghua University, Alexander Schwing , Richard , Raquel Urtasun U. of Toronto
• Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification ,Kyuyeon HwangSeoul National University, Wonyong Sung Seoul National University
• Variational inference for Monte Carlo objectives ,Andriy Mnih , Danilo Rezende Google DeepMind
• Hierarchical Decision Making In Electricity Grid Management ,Gal Dalal Technion, Elad Gilboa Technion, Shie MannorTechnion
• Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization ,Eric Balkanski , Baharan Mirzasoleiman ETH Zurich, Andreas Krause , Yaron Singer
• Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units ,Wenling Shang , Kihyuk Sohn NEC Laboratories America, Diogo Almeida Enlitic, Honglak Lee University of Michigan
• Isotonic Hawkes Processes ,Yichen Wang Georgia Tech, Bo Xie , Bo Dai Georgia Tech, Nan Du , Le Song Gatech
• Cross-graph Learning of Multi-relational Associations ,Hanxiao Liu , Yiming Yang
• Markov-modulated marked Poisson processes for check-in data ,Jiangwei Pan Duke University, Vinayak Rao Purdue University, Pankaj Agarwal Duke Univeristy, Alan Gelfand Duke University
• Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference ,Tudor Achim Stanford University, Ashish Sabharwal Allen Institute for AI, Stefano Ermon
• On the Power of Distance-Based Learning ,Periklis Papakonstantinou Rutgers University , Jia Xu Chinese Academy of Sciences, Guang Yang ICT
• A Convex Atomic-Norm Approach to Multiple Sequence Alignment and Motif Discovery ,Xin Lin University of Texas at Austin, Ian En-Hsu Yen University of Texas at Austin, Jiong Zhang University of Texas at Austin, Pradeep Ravikumar UT Austin, Inderjit
• Generalized Direct Change Estimation in Ising Model Structure ,Farideh Fazayeli University of Minnesota, Arindam Banerjee
• Robust Principal Component Analysis with Side Information ,Kai-Yang Chiang UT Austin, Cho-Jui Hsieh UC Davis, Inderjit
• Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation ,Huan Gui University of Illinois at Urba, Jiawei Han university of illinois at urbana-champaign, Quanquan Gu
• Early and Reliable Event Detection Using Proximity Space Representation ,Maxime Sangnier LTCI, Jerome Gauthier CEA, Alain Rakotomamonjy
• Stratified Sampling Meets Machine Learning ,Edo Liberty , Kevin Lang Yahoo Labs, Konstantin Shmakov Yahoo Labs
• Efficient Multi-Instance Learning for Activity Recognition from Time Series Data Using an Auto-Regressive Hidden Markov Model ,Xinze Guan Oregon State University, Raviv Raich Oregon State University, Weng-keen
• Generalization Properties and Implicit Regularization for Multiple Passes SGM ,Junhong Lin Istituto Italiano di Tecnologi, Raffaello Camoriano IIT (Italy) and UNIGE (Italy), Lorenzo Rosasco Istituto Italiano di Tecnologia
• Principal Component Projection Without Principal Component Analysis ,Roy Frostig Stanford University, Cameron MuscoMassachusetts Institute of Technology, Christopher Musco Mass. Institute of Technology, Aaron Sidford Microsoft Research
• Recovery guarantee of weighted low-rank approximation via alternating minimization ,Yuanzhi Li Princeton University, Yingyu Liang Princeton, Andrej Risteski Princeton University
• Deconstructing the Ladder Network Architecture ,Mohammad Pezeshki Universite de Montreal, Linxi Fan , Philemon Brakel , Aaron Courville , Yoshua Bengio U. of Montreal
• Generalization and Exploration via Randomized Value Functions ,Ian Osband Stanford, Ben , Zheng Wen Adobe Research
• Evasion and Hardening of Tree Ensemble Classifiers ,Alex Kantchelian University of California, J. D. Tygar UC Berkeley, Anthony Joseph UC Berkeley
• Dynamic Memory Networks for Visual and Textual Question Answering ,Caiming Xiong MetaMind, Stephen Merity MetaMind, Richard Socher
• Estimating Cosmological Parameters from the Dark-Matter Distribution ,Siamak Ravanbakhsh CMU, Sebastian FromenteauCarnegie Mellon Unitversity, Junier Oliva CMU, Layne Price Carnegie Mellon Unitversity, Shirley Ho Carnegie Mellon Unitversity, Barnabas Poczos , Jeff Schneider Carnegie Mellon Unitversity
• Learning population-level diffusions with generative RNNs ,Tatsunori Hashimoto MIT, David Gifford MIT, Tommi Jaakkola MIT
• Expressiveness of Rectifier Neural Network ,Xingyuan Pan University of Utah, Vivek Srikumar University of Utah
• Discrete Distribution Estimation under Local Privacy ,Peter Kairouz UIUC, Keith Bonawitz Google, Daniel Ramage
• Square Root Graphical Models: Multivariate Generalizations of Univariate Exponential Families which Allow Positive Dependencies ,David Inouye University of Texas at Austin, Pradeep Ravikumar UT Austin, Inderjit
• A Box-Constrained Approach for Hard Permutation Problems ,Cong Han Lim Univ of Wisconsin – Madison, Steve WrightUniversity of Wisconsin-Madison
• Geometric Mean Metric Learning ,Pourya Zadeh Tehran university, Reshad Hosseini , Suvrit Sra
• Sparse Nonlinear Regression: Parameter Estimation and Asymptotic Inference ,Zhuoran Yang Princeton University, Zhaoran Wang Princeton University, Han , Yonina Eldar Technion, Tong Zhang
• Conditional Bernoulli Mixtures for Multi-label Classification ,Cheng Li Northeastern University, Bingyu Wang Northeastern University, Virgil Pavlu Northeastern University, Javed Aslam Northeastern University
• Scalable Discrete Sampling as a Multi-Armed Bandit Problem ,Yutian Chen University of Cambridge, Zoubin
• Recycling Randomness with Structure for Sublinear time Kernel Expansions ,Krzysztof Choromanski Google Research NYC, Vikas Sindhwani Google Research
• Bidirectional Helmholtz Machines ,Jorg Bornschein University of Montreal, Samira Shabanian University of Montreal, Asja Fischer , Yoshua Bengio U. of Montreal
• Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier ,Jacob Abernethy U. of Michigan, Elad Hazan Princeton University
• Preconditioning Kernel Matrices ,Kurt Cutajar EURECOM, Michael Osborne , John Cunningham Columbia University, Maurizio Filippone EURECOM
• Greedy Column Subset Selection: New Bounds and Distributed Algorithms ,Jason Altschuler Princeton University, Aditya Bhaskara , Gang Fu Google Research, Vahab Mirrokni Google Research, Afshin Rostamizadeh Google, Morteza ZadimoghaddamGoogle Research
• Dynamic Capacity Networks ,Amjad Almahairi , Nicolas Ballas , Tim Cooijmans University of Montreal, Yin Zheng Hulu LLC., Hugo Larochelle Twitter, Aaron Courville
• Pricing a low-regret seller ,Hoda Heidari , Mohammad Mahdian Google, Umar Syed , Sergei Vassilvitskii , Sadra YazdanbodGeorgia Institute of Technology
• Estimation from Indirect Supervision with Linear Moments ,Aditi Raghunathan IIT Madras, Roy Frostig Stanford University, John , Percy Liang Stanford
• Speeding up k-means by approximating Euclidean distances via block vectors ,Thomas Bottesch Ulm University, Thomas Bühler Avira, Markus Kächele Ulm University
• Learning and Inference via Maximum Inner Product Search ,Stephen Mussmann Stanford University, Stefano Ermon
• A Superlinearly-Convergent Proximal Newton-type Method for the Optimization of Finite Sums ,Anton Rodomanov Higher School of Economics, Dmitry Kropotov Moscow State University
• A Kernel Test of Goodness of Fit ,Kacper.chwialkowski@ Chwialkowski Ucl, Heiko Strathmann University College London, Arthur Gretton UCL Gatsby
• Interacting Particle Markov Chain Monte Carlo ,Tom Rainforth University of Oxford, Christian Naesseth Linköping University, Brooks Paige University of Oxford, Frank Wood , Jan-Willem Vandemeent , Fredrik Lindsten Uppsala University
• Faster Eigenvector Computation via Shift-and-Invert Preconditioning ,Dan Garber TTI Chicago, Elad Hazan Princeton University, Chi Jin UC Berkeley, Sham , Cameron Musco Massachusetts Institute of Technology, Praneeth Netrapalli Microsoft Research, Aaron Sidford Microsoft Research
• A Theory of Generative ConvNet ,Jianwen Xie UCLA, Yang Lu UCLA, Song-Chun Zhu UCLA, Yingnian Wu UCLA
• Efficient Learning with Nonconvex Regularizers by Nonconvexity Redistribution ,Quanming Yao HKUST, James Kwok Hong Kong University Science Technology
• Computationally Efficient Nystr\”{o}m Approximation using Fast Transforms ,Si Si , Cho-Jui Hsieh UC Davis, Inderjit
• Gromov-Wasserstein Barycenters of Similarity Matrices ,Gabriel , Justin Solomon , Marco Cuturi Kyoto
• Robust Monte Carlo Sampling using Riemannian Nos\'{e}-Poincar\'{e} Hamiltonian Dynamics ,Anirban Roychowdhury , Brian Kulis Boston University, Srinivasan Parthasarathy
• The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM ,Ardavan Saeedi MIT, Matthew Hoffman Adobe Research, Ryan Adams Harvard, Matthew Johnson
• Meta–Gradient Boosted Decision Tree Model for Weight and Target Learning ,Yury Ustinovskiy Yandex, Valentina FedorovaYandex, Gleb Gusev Yandex, Pavel Serdyukov Yandex
• Discriminative Embeddings of Latent Variable Models for Structured Data ,Hanjun Dai Georgia Tech, Bo Dai Georgia Tech, Le Song Gatech
• Robust Random Cut Forest Based Anomaly Detection on Streams ,Sudipto Guha , Nina Mishra , Gourav Roy , Okke Schrijvers
• Training Neural Networks Without Gradients: A Scalable ADMM Approach ,Tom Goldstein University of Maryland, Gavin Taylor US Naval Academy, Ankit Patel Rice University, Ryan Burmeister US Naval Academy, Zheng Xu University of Maryland, Bharat Singh University of Maryland
• Topographical Features of High-Dimensional Categorical Data and Their Applications to Clustering ,Chao Chen CUNY, Novi Quadrianto University of Sussex
• Efficient Algorithms for Large-scale Generalized Eigenvector Computation and CCA ,Rong Ge , Chi Jin UC Berkeley, Sham , Praneeth Netrapalli Microsoft Research, Aaron Sidford Microsoft Research
• Algorithms for Optimizing the Ratio of Submodular Functions ,Wenruo Bai University of Washington, Rishabh Iyer , Kai Wei , Jeff Bilmes U. of Washington
• Model-Free Imitation Learning with Policy Optimization ,Jonathan Ho Stanford, Jayesh Gupta Stanford University, Stefano Ermon
• ADIOS: Architectures Deep In Output Space ,Moustapha Cisse , Maruan Al-Shedivat CMU, Samy Bengio Google
• Causal Strength via Shannon Capacity: Axioms, Estimators and Applications ,Weihao Gao UIUC, Sreeram Kannan UW Seattle, Sewoong Oh UIUC, Pramod Viswanath UIUC
• Memory-based Control of Active Perception and Action in Minecraft ,Junhyuk Oh University of Michigan, Valliappa Chockalingam University of Michigan, Satinder , Honglak Lee University of Michigan
• The Label Complexity of Mixed-Initiative Classifier Training ,Jina Suh Microsoft, Xiaojin Zhu University of Wisconsin, Saleema Amershi Microsoft
• Bayesian Poisson Tucker Decomposition for Learning the Structure of International Relations ,Aaron Schein , Mingyuan Zhou , Blei David Columbia, Hanna Wallach Microsoft
• Tensor Decomposition via Joint Matrix Schur Decomposition ,Nikos Vlassis Adobe, Nicolo Colombo Univ of Luxembourg
• Improving the Efficiency of Deep Reinforcement Learning with Normalized Advantage Functions and Synthetic Experience ,Shixiang Gu University of Cambridge, Sergey Levine Google, Timothy Lillicrap Google DeepMind, Ilya SutskeverOpenAI
• Domain Adaptation with Conditional Transferable Components ,Mingming Gong University of Technology Sydne, Kun ZhangCarnegie Mellon University, Tongliang Liu MPI Tuebingen, Dacheng Tao , Bernhard Schölkopf
• Fixed Point Quantization of Deep Convolutional Networks ,Darryl Lin Qualcomm Research, Sachin Talathi Qualcomm Research, Sreekanth Annapureddy NetraDyne Inc.
• Provable Algorithms for Inference in Topic Models ,Sanjeev Arora Princeton University, Rong Ge , Frederic Koehler Princeton University, Tengyu Ma Princeton University, Ankur Moitra
• Epigraph projections for fast general convex programming ,Po-Wei Wang Carnegie Mellon University, Matt Wytock , Zico
• Fast Algorithms for Segmented Regression ,Ludwig Schmidt , Jerry Li MIT, Jayadev Acharya MIT, Ilias Diakonikolas
• Energetic Natural Gradient Descent ,Philip Thomas CMU, Christoph Dann Carnegie Mellon University, Bruno Castro da Silva , Emma
• Partition Functions from Rao-Blackwellized Tempered Sampling ,Patrick Stinson Columbia University, David CarlsonColumbia University, Ari Pakman Columbia University, Liam
• Learning Mixtures of Plackett-Luce Models ,Zhibing Zhao RPI, Peter Piech RPI, Lirong Xia RPI
• Near Optimal Behavior via Approximate State Abstraction ,David Abel Brown University, David Hershkowitz Brown University, Michael Littman
• Power of Ordered Hypothesis Testing ,Lihua Lei Lihua, William Fithian UC Berkeley
• PHOG: Probabilistic Model for Code ,Pavol Bielik ETH Zurich, Veselin Raychev ETH Zurich, Martin Vechev ETH Zurich
• Shifting Regret, Mirror Descent, and Matrices ,Andras Gyorgy , Csaba Szepesvari Alberta
• Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters ,Jelena Luketina Aalto University, Tapani Raiko , Mathias Berglund Aalto University
• Model-Free Trajectory Optimization\\ for Reinforcement Learning of Motor Skills ,Riad Akrour TU Darmstadt, Gerhard Neumann
• Controlling the distance to a Kemeny consensus without computing it ,Anna Korba Telecom Paris Tech, Yunlong Jiao Mines Paris Tech, Eric Sibony Telecom Paris Tech
• Horizontally Scalable Submodular Maximization ,Mario Lucic ETH Zurich, Olivier Bachem ETH Zurich, Morteza Zadimoghaddam Google Research, Andreas Krause
• Group Equivariant Convolutional Networks ,Taco Cohen University of Amsterdam, Max Welling University of Amsterdam / CIFAR
• Stochastic Discrete Clenshaw-Curtis Quadrature ,Nico Piatkowski TU Dortmund, Katharina
• Correcting Forecasts with Multi-force Neural Attention ,Matthew Riemer IBM, Aditya Vempaty IBM, Flavio Calmon IBM, Fenno Heath IBM, Richard Hull IBM, Elham Khabiri IBM
• Learning Representations for Counterfactual Inference ,Uri Shalit , David Sontag NYU, Fredrik Johansson Chalmers Technical University
• The Automatic Statistician: A Relational Perspective ,Yunseong Hwang UNIST, Anh Tong UNIST, Jaesik Choi UNIST
• Inference Networks for Sequential Monte Carlo in Graphical Models ,Brooks Paige University of Oxford, Frank Wood
• Slice Sampling on Hamiltonian Trajectories ,Benjamin Bloem-Reddy Columbia University, John Cunningham Columbia University
• Noisy Activation Functions ,Caglar Gülçehre , Marcin Moczulski , Misha Denil , Yoshua Bengio U. of Montreal
• A Primal and Dual Sparse Approach to Extreme Classification ,Ian En-Hsu Yen University of Texas at Austin, Xiangru HuangUTaustin, Pradeep Ravikumar UT Austin, Kai Zhong ICES department, Inderjit