Skip to yearly menu bar Skip to main content

NIPS 2015 Accepted Papers

Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing
Nihar Shah*, UC Berkeley; Dengyong Zhou, MSR

Learning with Symmetric Label Noise: The Importance of Being Unhinged
Brendan van Rooyen, NICTA; Aditya Menon*, NICTA; Robert Williamson, NICTA

Algorithmic Stability and Uniform Generalization
Ibrahim Alabdulmohsin*, KAUST

Adaptive Low-Complexity Sequential Inference for Dirichlet Process Mixture Models
Theodoros Tsiligkaridis*, MIT Lincoln Laboratory; Keith Forsythe, MIT Lincoln Laboratory

Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling
Xiaocheng Shang, University of Edinburgh; Zhanxing Zhu*, University of Edinburgh; Benedict Leimkuhler, University of Edinburgh; Amos J. Storkey, University of Edinburgh

Robust Portfolio Optimization
Huitong Qiu*, Johns Hopkins University; Fang Han, ; Han Liu, Princeton University; Brian Caffo,

Logarithmic Time Online Multiclass prediction
Anna Choromanska*, Courant Institute, NYU; John Langford, Microsoft Research New York

Planar Ultrametric Rounding for Image Segmentation
Julian Yarkony*, Dr.; Charless Fowlkes, UC Irvine

Expressing an Image Stream with a Sequence of Natural Sentences
Cesc Park, Seoul National University; Gunhee Kim*, Seoul National University

Parallel Correlation Clustering on Big Graphs
Xinghao Pan*, UC Berkeley; Dimitris Papailiopoulos, UC Berkeley; Benjamin Recht, UC Berkeley; Kannan Ramchandran, UC Berkeley; Michael Jordan, UC Berkeley

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, USTC; Kaiming He*, Microsoft Research Asia; Ross Girshick, Microsoft Research; Jian Sun, Microsoft Research Asia

Space-Time Local Embeddings
Ke SUN*, University of Geneva; Jun Wang, Expedia, Geneva; Alexandros Kalousis, ; Stephane Marchand-Maillet, University of Geneva

A Convergent Gradient Descent Algorithm for Rank Minimization and Semidefinite Programming from Random Linear Measurements
Qinqing Zheng*, University of Chicago; John Lafferty, University of Chicago

Smooth Interactive Submodular Set Cover
Bryan He*, Caltech; Yisong Yue, Caltech

Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
Jiajun Wu*, MIT; Ilker Yildirim, MIT; William Freeman, MIT; Josh Tenenbaum, MIT

On the Pseudo-Dimension of Nearly Optimal Auctions
Jamie Morgenstern*, University of Pennsylvania; Tim Roughgarden,

Unlocking neural population non-stationarities using hierarchical dynamics models
Mijung Park*, UCL; Gergo Bohner, Gatsby Unit, UCL; Jakob Macke,

Bayesian Manifold Learning: Locally Linear Latent Variable Model (LL-LVM)
Mijung Park*, UCL; Wittawat Jitkrittum, Gatsby unit, UCL; Ahmad Qamar, ; Zoltan Szabo, UCL; Lars Buesing, ; Maneesh Sahani,

Color Constancy by Learning to Predict Chromaticity from Luminance
Ayan Chakrabarti*, TTI Chicago

Fast and Accurate Inference of Plackett–Luce Models
Lucas Maystre*, EPFL; Matthias Grossglauser, EPFL

Probabilistic Line Searches for Stochastic Optimization
Maren Mahsereci, MPI for Intelligent Systems; Philipp Hennig*, MPI Tübingen

Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
Armand Joulin*, Facebook AI research; Tomas Mikolov, Facebook AI Research

Where are they looking?
Adria Recasens*, MIT; Aditya Khosla, MIT; Carl Vondrick, MIT; Antonio Torralba, MIT

Minimax Regret for Unfair Bandits 004
Tor Lattimore*, University of Alberta

On the Limitation of Spectral Methods: From the Gaussian Hidden Clique Problem to Rank-One Perturbations of Gaussian Tensors
Daniel Reichman*, Cornell University; Andrea Montanari, Stanford; Ofer Zeitouni, Weizmann Institute and Courant Institute

Measuring Sample Quality with Stein's Method
Jack Gorham, Stanford University; Lester Mackey*, Stanford

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
Yan Huang*, CRIPAC, CASIA; Wei Wang, NLPR,CASIA; Liang Wang,

Bounding errors of Expectation-Propagation
Guillaume Dehaene*, University of Geneva; Simon Barthelmé, Gipsa-lab CNRS

A fast, universal algorithm to learn parametric nonlinear embeddings
Miguel Carreira-Perpinan*, UC Merced; Maksym Vladymyrov, Yahoo

Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks
Leon Gatys*, University of Tübingen; Alexander Ecker, University of Tuebingen; Matthias Bethge, CIN, University Tübingen

Extending Gossip Algorithms to Distributed Estimation of U-statistics
Igor Colin*, Télécom ParisTech; Aurélien Bellet, Telecom ParisTech; Joseph Salmon, Telecom Paristech; Stéphan Clémençon, Telecom ParisTech

Streaming, Distributed Variational Inference for Bayesian Nonparametrics
Trevor Campbell*, MIT; Julian Straub, Mit; John Fisher, MIT; Jonathan How,

Learning visual biases from human imagination
Carl Vondrick*, MIT; Hamed Pirsiavash, MIT; Aude Oliva, MIT; Antonio Torralba, MIT

Smooth and Strong: MAP Inference with Linear Convergence
Ofer Meshi*, TTI Chicago; Mehrdad Mahdavi, TTI Chicago; Alex Schwing, University of Toronto

Copeland Dueling Bandits
Masrour Zoghi*, University of Amsterdam; Zohar Karnin, Yahoo Labs ; Shimon Whiteson, University of Amsterdam; Maarten de Rijke, University of Amsterdam

Optimal Ridge Detection using Coverage Risk
Yen-Chi Chen*, Carnegie Mellon University; Christopher Genovese, Carnegie Mellon University; Shirley Ho, Carnegie Mellon University; Larry Wasserman, Carnegie Mellon University

Top-$k$ Multiclass SVM
Maksim Lapin*, MPI Informatics; Matthias Hein, Saarland University; Bernt Schiele, Max Planck Institute for Informatics

Policy Evaluation Using the Ω-Return
Philip Thomas*, ; George Konidaris, Duke; Scott Niekum, UT Austin; Georgios Theocharous, Adobe

Orthogonal NMF through Subspace Exploration
Megasthenis Asteris*, University of Texas at Austin; Dimitris Papailiopoulos, UC Berkeley; Alex Dimakis, Utaustin

Stochastic Online Greedy Learning with Semi-bandit Feedbacks
Tian Lin*, Tsinghua University; Jian Li, Tsinghua University; Wei Chen,

Deeply Learning the Messages in Message Passing Inference
Guosheng Lin*, The University of Adelaide; Chunhua Shen, ; Ian Reid, University of Adelaide; Anton Van Den Hengel, University of Adelaide

Synaptic Sampling: A Bayesian Approach to Neural Network Plasticity and Rewiring
David Kappel*, Graz University of Technology; Stefan Habenschuss, ; Robert Legenstein, ; Wolfgang Maass,

Accelerated Proximal Gradient Methods for Nonconvex Programming
Li Huan, Peking University; Zhouchen Lin*, Peking University

Approximating Sparse PCA from Incomplete Data

Influence Functions for Machine Learning: Nonparametric Estimators for Entropies, Divergences and Mutual Informations
Kirthevasan Kandasamy*, CMU; Akshay Krishnamurthy, CMU; Barnabas Poczos, Carnegie Mellon University; Larry Wasserman, Carnegie Mellon University; James Robins, Harvard University

Column Selection via Adaptive Sampling
Saurabh Paul*, Rensselaer Polytechnic Inst.; Malik Magdon-Ismail, RPI; Petrod Drineas,

HONOR: Hybrid Optimization for NOn-convex Regularized problems
Pinghua Gong*, University of Michigan-Ann Arbor; Jieping Ye, University of Michigan

3D Object Proposals for Accurate Object Class Detection
Xiaozhi Chen, Tsinghua University; Kaustav Kundu, University of Toronto; Yukun Zhu, University of Toronto; Andrew Berneshawi, University of Toronto; Huimin Ma, Tsinghua University; Sanja Fidler, University of Toronto; Raquel Urtasun*, University of Toronto

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits
Huasen Wu*, University of California, Davi; R. Srikant, University of Illinois, Urbana-Champaign; Xin Liu, University of California, Davis; Chong Jiang, University of Illinois, Urbana-Champaign

Tensorizing Neural Networks
Alexander Novikov*, Skolkovo institute of science ; Dmitry Podoprihin, msu; Anton Osokin, Inria; Dmitry Vetrov,

Parallelizing MCMC with Random Partition Trees
Xiangyu Wang, Duke University; Fangjian Guo*, Duke University; Katherine Heller, Duke University; David Dunson, Duke University

A Reduced-Dimension fMRI Shared Response Model
Po-Hsuan Chen*, Princeton University; Janice Chen, ; Yaara Yeshurun-Dishon, ; Uri Hasson, Princeton University; James Haxby, ; Peter Ramadge, Princeton

Spectral Learning of Large Structured HMMs for Comparative Epigenomics
Chicheng Zhang, UC San Diego; Jimin Song, Rutgers; Kamalika Chaudhuri, UCSD; Kevin Chen*, Rutgers

Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability
Xia Qu, Epic Systems; Prashant Doshi*, University of Georgia

Estimating Mixture Models via Mixtures of Polynomials
Sida Wang*, Stanford University; percy Liang, Stanford University; Arun Chaganty, Stanford

On the Global Linear Convergence of Frank-Wolfe Optimization Variants
Simon Lacoste-Julien*, INRIA; Martin Jaggi, ETH Zurich

Deep Knowledge Tracing
Chris Piech*, Stanford; Jonathan Bassen,; Jonathan Huang,; Surya Ganguli,; Mehran Sahami,; Leonidas Guibas,; Jascha Sohl-Dickstein,

Moment matching for LDA and discrete ICA
Anastasia Podosinnikova*, INRIA/ENS; Simon Lacoste-Julien, INRIA; Francis Bach, INRIA - ENS

Efficient Compressive Phase Retrieval with Constrained Sensing Vectors
Sohail Bahmani*, Georgia Tech.; Justin Romberg, Georgia Institute of Technology

Barrier Frank-Wolfe for Marginal Inference
Rahul Krishnan*, New York University; Simon Lacoste-Julien, INRIA; David Sontag, NYU

Learning Theory and Algorithms for Forecasting Non-stationary Time Series
Vitaly Kuznetsov*, Courant Institute; Mehryar Mohri, Courant Institute and Google

Compressive spectral embedding: sidestepping the SVD
Dinesh Ramasamy*, UC Santa Barbara; Upamanyu Madhow, UC Santa Barbara

A Nonconvex Optimization Framework for Low Rank Matrix Estimation
Tuo Zhao*, ; Zhaoran Wang, Princeton University; Han Liu, Princeton University

Automatic Variational Inference in Stan
Alp Kucukelbir*, ; Rajesh Ranganath, Princeton University; Andrew Gelman, Columbia University; David Blei, Columbia University

Attention-Based Models for Speech Recognition
Jan Chorowski*, University of Wroclaw; Dzmitry Bahdanau, Jacobs University, Germany; Dmitriy Serdyuk, Université de Montréal; Kyunghyun Cho, NYU; Yoshua Bengio, U. Montreal

Closed-form Estimators for High-dimensional Generalized Linear Models
Eunho Yang*, IBM Thomas J. Watson Research Center; Aurelie Lozano, IBM Research; Pradeep Ravikumar, University of Texas at Austin

Online F-Measure Optimization
Robert Busa-Fekete*, UPB; Balazs Szorenyi, The Technion/University of Szeged; Krzysztof Dembczynski, PUT; Eyke Hullermeier, Marburguniversity

Online Rank Elicitation for Plackett-Luce: A Dueling Bandits Approach
Balazs Szorenyi, The Technion/University of Szeged; Robert Busa-Fekete*, UPB; Adil Paul, UPB; Eyke Hullermeier, Marburguniversity

On Submodularity of M-Best-Diverse-Labelings
Alexander Kirillov*, MSU; Dmitrij Schlesinger, TU Dresden; Dmitry Vetrov, ; Carsten Rother, TU Dresden; Bogdan Savchynskyy, TU Dresden

Tractable Bayesian Network Structure Learning with Bounded Vertex Cover Number
Janne Korhonen, University of Helsinki; Pekka Parviainen*, Aalto University

Learning Large-Scale Poisson DAG Models based on OverDispersion Scoring
Gunwoong Park*, UW, Madison; Garvesh Raskutti, University of Wisconsin, Madison

Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy
Marylou Gabrie, Ecole Normale Superieure; Eric Tramel, LPS, École Normale Supérieure; Florent Krzakala*, Ecole Normale Superieure CNRS

Character-level Convolutional Networks for Text Classification
Xiang Zhang*, New York University; Junbo Zhao, New York University; Yann LeCun, New York University

Semi-Supervised Robust Feature-Sample Linear Discriminant Analysis for Neurodegenerative Brain Disorders Diagnosis
Ehsan Adeli-M.*, UNC-Chapel Hill; Kim-Han Thung, UNC-Chapel Hill; Le An, UNC-Chapel Hill; Feng Shi, UNC-Chapel Hill; Dinggang Shen, UNC-Chapel Hill

Black-box optimization of noisy functions with unknown smoothness
jean-bastien grill, INRIA Lille - Nord Europe; Michal Valko*, INRIA Lille - Nord Europe; Remi Munos, INRIA Lille

Recovering Communities in the General Stochastic Block Model Without Knowing the Parameters
Emmanuel Abbe*, Princeton University; Colin Sandon, Princeton University

Deep learning with Elastic Averaging SGD
Sixin Zhang*, New York University; Anna Choromanska, Courant Institute, NYU; Yann LeCun, New York University

Monotone k-Submodular Function Maximization with Size Constraints
Naoto Ohsaka*, The University of Tokyo; Yuichi Yoshida, National Institute of Informatics

Active Learning from Weak and Strong Labelers
Chicheng Zhang*, UC San Diego; Kamalika Chaudhuri, UCSD

On the Optimality of Classifier Chain for Multi-label Classification
Weiwei Liu*, UTS; Ivor Tsang, "University of Technology, Sydney"

Robust Regression via Hard Thresholding
Purushottam Kar*, Microsoft Research India; Prateek Jain, Microsoft Research; Kush Bhatia, Microsoft Research

Locally Non-linear Embeddings for Extreme Multi-label Learning
Purushottam Kar*, Microsoft Research India; Prateek Jain, Microsoft Research; Manik Varma, Microsoft Research India; Kush Bhatia, Microsoft Research; Himanshu Jain, IIT Delhi

Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems
Yuxin Chen*, Stanford University; Emmanuel Candes, Stanford University

A Hierarchical Approach to Individualized Disease Trajectory Predictions in Heterogeneous Populations
Peter Schulam*, Johns Hopkins University; Suchi Saria, Johnshopkins

Subspace Clustering with Irrelevant Features via Robust Dantzig Selector
Chao Qu*, NUS; Huan Xu, National University of Singapore

Sparse PCA via Bipartite Matchings
Megasthenis Asteris*, University of Texas at Austin; Dimitris Papailiopoulos, UC Berkeley; Anastasios Kyrillidis, University of Texas at Austin; Alex Dimakis, Utaustin

Fast Randomized Kernel Methods with Statistical Guarantees
Ahmed El Alaoui*, UC Berkeley; Michael Mahoney, UC Berkeley

Online Learning for Adversaries with Memory: Price of Past Mistakes
Oren Anava*, Technion; Elad Hazan, Princeton University; Shie Mannor, Technion

Convolutional spike-triggered covariance analysis for neural subunit models
Anqi Wu*, Princeton University; Memming Park, Stony Brook; Jonathan Pillow, Princeton University

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
Xingjian Shi*, HKUST; Zhourong Chen, The Hong Kong University of Science and Technology; Hao Wang, HKUST; Dit Yan Yeung, HKUST; Wai-kin Wong, ; Wang-chun WOO,

GAP Safe screening rules for sparse multi-task and multi-class models
Eugene Ndiaye, Institut Mines-Télécom, Télécom ParisTech, CNRS LTCI; Olivier Fercoq, Telecom ParisTech; Alexandre Gramfort*, Telecom Paristech; Joseph Salmon, Telecom Paristech

Empirical Localization of Homogeneous Divergences on Discrete Sample Spaces
Takashi Takenouchi*, Future University Hakodate; Takafumi Kanamori, Nagoya University

Statistical Model Criticism using Kernel Two Sample Tests
James Lloyd*, University of Cambridge; Zoubin Ghahramani, University of Cambridge

Precision-Recall-Gain Curves: PR Analysis Done Right
Peter Flach*, University of Bristol; Meelis Kull, University of Bristol

A Generalization of Submodular Cover via the Diminishing Return Property on the Integer Lattice
Tasuku Soma*, University of Tokyo; Yuichi Yoshida, National Institute of Informatics

Bidirectional Recurrent Neural Networks as Generative Models
Mathias Berglund*, Aalto University; Tapani Raiko, Aalto University; Mikko Honkala, Nokia Labs; Leo Kärkkäinen, Nokia Labs; Akos Vetek, Nokia Labs; Juha Karhunen, Aalto University

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling
Zheng Qu*, University of Edinburgh; Peter Richtarik, University of Edinburgh; Tong Zhang, Rutgers

Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets
Justin Domke*, NICTA

Hessian-Free Optimization For Learning Deep Multidimensional Recurrent Neural Networks
Minhyung Cho*, Gracenote; Jaehyung Lee, Gracenote; Chandra Dhir, Gracenote

Large-scale probabilistic predictors with and without guarantees of validity
Vladimir Vovk*, Royal Holloway, Univ of London; Ivan Petej, ; Valentina Fedorova,

Shepard Convolutional Neural Networks
Jimmy Ren*, SenseTime Group Limited; Li Xu, SenseTime Group Limited; Qiong Yan, SenseTime Group Limited; Wenxiu Sun, SenseTime Group Limited

Manifold Optimization for Gaussian Mixture Models
Reshad Hosseini*, University of Tehran; Suvrit Sra, MIT

Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding
Rie Johnson*, RJ Research Consuulting; Tong Zhang, Rutgers

Parallel Recursive Best-First AND/OR Search for Exact MAP Inference in Graphical Models
Akihiro Kishimoto*, IBM Research; Radu Marinescu, IBM Research, Ireland; Adi Botea, IBM Research

Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling
Ming Liang, Tsinghua University; Xiaolin Hu*, Tsinghua University; Bo Zhang, Tsinghua University

Bounding the Cost of Search-Based Lifted Inference
David Smith*, University of Texas at Dallas; Vibhav Gogate, UT Dallas

Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families
Heiko Strathmann*, University College London; Dino Sejdinovic, University of Oxford; Samuel Livingstone, University College London; Zoltan Szabo, UCL; Arthur Gretton, University Collage London

Linear Multi-Resource Allocation with Semi-Bandit Feedback
Tor Lattimore*, University of Alberta; Csaba Szepesvari, University of Alberta; Koby Crammer, Technion

Unsupervised Learning by Program Synthesis
Kevin Ellis*, MIT; Josh Tenenbaum, MIT; Armando Solar-Lezama, MIT

Enforcing balance allows local supervised learning in spiking recurrent networks
Ralph Bourdoukan*, Ecole Normale Superieure; Sophie Deneve, GNT, Ecole Normale Superieure

Fast and Guaranteed Tensor Decomposition via Sketching
Yining Wang*, Carnegie Mellon University; Hsiao-Yu Tung, Carnegie Mellon University; Animashree Anandkumar, UC Irvine; Alex Smola, Carnegie Mellon University

Differentially private subspace clustering
Yining Wang*, Carnegie Mellon University; Yu-Xiang Wang, CMU; Aarti Singh, CMU

Predtron: A Family of Online Algorithms for General Prediction Problems
Prateek Jain, Microsoft Research; Nagarajan Natarajan, UT Austin; Ambuj Tewari*, University of Michigan

Weighted Theta Functions and Embeddings with Applications to Max-Cut, Clustering and Summarization
Fredrik Johansson*, Chalmers University, Sweden; Ankani Chattoraj, Chalmers University; Devdatt Dubhashi, Chalmers University, Sweden; Chiranjib Bhattacharyya, Indian Institute of Science

SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk
Guillaume Papa*, Telecom paristech; Stéphan Clémençon, Telecom ParisTech; Aurélien Bellet, Telecom ParisTech

On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs
Wei Cao*, Tsinghua University; Jian Li, Tsinghua University; Yufei Tao, CUHK; Zhize Li, Tsinghua University

The Brain Uses Reliability of Stimulus Information when Making Perceptual Decisions
Sebastian Bitzer*, TU Dresden; Stefan Kiebel, TU Dresden

Fast Classification Rates for High-dimensional Conditional Gaussian Models
Tianyang Li*, UT Austin; Adarsh Prasad, UT Austin; Pradeep Ravikumar, University of Texas at Austin

Fast Distributed k-Center Clustering with Outliers on Massive Data
Gustavo Malkomes, Washington University in St. Louis; Matt Kusner, Washington University in STL; Wenlin Chen, Washington University in St. Louis; Kilian Weinberger, Washington University in St. Louis; Benjamin Moseley*, Washington University in St Lo

Human Memory Search as Initial-Visit Emitting Random Walk
Kwang-Sung Jun*, University of Wisconsin-Madiso; Xiaojin Zhu, University of Wisconsin-Madison; Timothy Rogers, University of Wisconsin-Madison; Zhuoran Yang, Tsinghua University; ming yuan, University of Wisconsin - Madison

Non-convex Statistical Optimization for Sparse Tensor Graphical Model
Wei Sun*, Purdue University; Zhaoran Wang, Princeton University; Han Liu, Princeton University; Guang Cheng, Purdue University

Convergence Rates of Active Learning for Maximum Likelihood Estimation
Kamalika Chaudhuri, UCSD; Sham Kakade, University of Washington; Praneeth Netrapalli*, Microsoft Research; Sujay Sangahvi, UTexas-Austin

Learning to Rotate 3D Objects with Recurrent Convolutional Encoder-Decoder Networks
Jimei Yang*, UC Merced; Scott Reed, University of Michigan; Ming-Hsuan Yang, UC Merced; Honglak Lee, U. Michigan

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
Pascal Vincent*, U. Montreal; Alexandre de Brébisson, Université de Montréal; Xavier Bouthillier, Universit de Montréal

Backpropagation for Energy-Efficient Neuromorphic Computing
Steve Esser*, IBM Research-Almaden; Rathinakumar Appuswamy, IBM Research-Almaden; Paul Merolla, IBM Research-Almaden; John Arthur, IBM Research-Almaden; Dharmendra Modha, IBM Research-Almaden

Alternating Minimization for Regression Problems with Vector-valued Outputs
Prateek Jain*, Microsoft Research; Ambuj Tewari, University of Michigan

Learning both Weights and Connections for Efficient Neural Network
Song Han*, Stanford University; Jeff Pool, NVIDIA ; John Tran, NVIDIA; Bill Dally , Stanford University & NVIDIA

Optimal Rates for Random Fourier Features
Bharath Sriperumbudur, The Pennsylvania State University; Zoltan Szabo*, UCL

The Population Posterior and Bayesian Inference on Streams
James McInerney*, Columbia; Rajesh Ranganath, Princeton University; David Blei, Columbia University

Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees
François-Xavier Briol*, University of Oxford; Chris. Oates, University of Tech., Sydney; Mark Girolami, Univeresity of Warwick; Mike Osborne, U Oxford

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Samy Bengio*, Google Research; Oriol Vinyals, Google; Navdeep Jaitly, Google; Noam Shazeer, Google

Unified View of Matrix Completion under General Structural Constraints
Suriya Gunasekar*, UT Austin; Arindam Banerjee, University of Minnesota; Joydeep Ghosh, UT Austin

Efficient Output Kernel Learning for Multiple Tasks
Pratik Jawanpuria*, Saarlanduniversity; Maksim Lapin, MPI Informatics; Matthias Hein, Saarland University; Bernt Schiele, Max Planck Institute for Informatics

Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models
Michael Hughes*, Brown University; William Stephenson, Brown University; Erik Sudderth, Brown University

Variational Consensus Monte Carlo
Maxim Rabinovich*, UC Berkeley; Elaine Angelino, Harvard; Michael Jordan, UC Berkeley

Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma
Murat Erdogdu*, Stanford University

Practical and Optimal LSH for Angular Distance
Ilya Razenshteyn*, MIT; Piotr Indyk, ; Ludwig Schmidt, ; Thijs Laarhoven, ; Alexandr Andoni,

Learning to Linearize Under Uncertainty
Ross Goroshin*, New York University; Michael Mathieu, New York University; Yann LeCun, New York University

Finite-Time Analysis of Projected Langevin Monte Carlo
Sebastien Bubeck*, MSR; Ronen Eldan, ; Joseph Lehec,

Deep Visual Analogy-Making
Scott Reed*, University of Michigan; Yi Zhang, University of Michigan; Yuting Zhang, University of Michigan; Honglak Lee, U. Michigan

Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation
Alaa Saade*, ENS; Florent Krzakala, Ecole Normale Superieure CNRS; Lenka Zdeborová, CEA

Online Learning with Adversarial Delays
Kent Quanrud*, UIUC; Daniel Khashabi, UIUC

Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection
Jie Wang*, University of Michigan-Ann Arbor; Jieping Ye, University of Michigan

Minimum Weight Perfect Matching via Blossom Belief Propagation
Sungsoo Ahn, KAIST; Sejun Park, KAIST; Michael Chertkov, ; Jinwoo Shin*, KAIST

Efficient Thompson Sampling for Online Matrix-Factorization Recommendation
Jaya Kawale*, Adobe Research; Hung Bui, Adobe Research; Branislav Kveton, Adobe Research; Long Tran-Thanh, University of Southampton; Sanjay Chawla, University of Sydney

Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems
Mingyi Hong*, ; Ruoyu Sun, Stanford university

Lifted Symmetry Detection and Breaking for MAP Inference
Timothy Kopp*, University of Rochester; Parag Singla, Indian Institute of Technology; Henry Kautz, University of Rochester

Evaluating the statistical significance of biclusters
Jason Lee, Stanford; Yuekai Sun*, Stanford University; Jonathan Taylor, Stanford University

Discriminative Robust Transformation Learning
Jiaji Huang*, Duke University; Qiang Qiu, Duke University; Guillermo Sapiro, ; Robert Calderbank, Duke University

Bandits with Unobserved Confounders: A Causal Approach
Elias Bareinboim*, ; Andrew Forney, UCLA; Judea Pearl, UCLA

Scalable Semi-Supervised Aggregation of Classifiers
Akshay Balsubramani*, Ucsd; Yoav Freund, UC San Diego

Online Learning with Gaussian Payoffs and Side Observations
Yifan Wu*, University of Alberta; Andras Gyorgy, University of Alberta; Csaba Szepesvari, Alberta

Private Graphon Estimation for Sparse Graphs
Christian Borgs, Microsoft Research; Jennifer Chayes, Microsoft Research; Adam Smith*,

SubmodBoxes: Near-Optimal Search for a Set of Diverse Object Proposals
Qing Sun, Virginia Tech; Dhruv Batra*, Virginia Tech

Fast Second Order Stochastic Backpropagation for Variational Inference
Kai Fan*, Duke University; Ziteng Wang, ; Jeff Beck, ; James Kwok, Hong Kong University of Science and Technology; Katherine Heller, Duke

Stronger and Faster Approximate Singular Value Decomposition via the Block Lanczos Method
Cameron Musco, Massachusetts Institute of Technology; Christopher Musco*, Mass. Institute of Technology

Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions
Yuya Yoshikawa*, NAIST; Tomoharu Iwata, Nippon Telegraph and Telephone Corporation; Hiroshi Sawada, NTT; Takeshi Yamada, NTT

Scalable Automated Inference for Gaussian Process Models
Amir Dezfouli, The University of New South Wales; Edwin Bonilla*, University of New South Wales

Fast Bidirectional Probability Estimation in Markov Models
Siddhartha Banerjee*, Cornell University; Peter Lofgren, Stanford University

Probabilistic Variational Bounds for Graphical Models
Qiang Liu*, MIT; alexander ihler, UC irvine; John Fisher, MIT

Linear Response Methods for Accurate Covariance Estimates from Mean Field Variational Bayes
Ryan Giordano*, UC Berkeley; Tamara Broderick, MIT; Michael Jordan, UC Berkeley

Combinatorial Cascading Bandits
Branislav Kveton*, Adobe Research; Zheng Wen, Yahoo; Azin Ashkan, Technicolor Research; Csaba Szepesvari, Alberta

Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path
Daniel Hsu*, Columbia University; Aryeh Kontorovich, Ben Gurion University; Csaba Szepesvari, Alberta

Policy Gradient for Coherent Risk Measures
Aviv Tamar*, Technion; Yinlam Chow, Stanford; Mohammad Ghavamzadeh, Adobe Research & INRIA; Shie Mannor, Technion

Fast Rates for Exp-concave Empirical Risk Minimization
Tomer Koren*, Technion; Kfir Levy, Technion

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
Emily Denton*, New York University; Rob Fergus, Facebook AI Research; Arthur Szlam, Facebook; Soumith Chintala, Facebook AI Research

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
Seunghoon Hong*, POSTECH; Hyeonwoo Noh, POSTECH; Bohyung Han, Postech

Equilibrated adaptive learning rates for non-convex optimization
Yann Dauphin*, Universit? de Montr?al; Harm de Vries, ; Yoshua Bengio, U. Montreal

BACKSHIFT: Learning causal cyclic graphs from unknown shift interventions
Dominik Rothenhäusler, ETH Zurich; Christina Heinze*, ETH Zurich; Jonas Peters, MPI T?bingen; Nicolai Meinshausen, ETH Zurich

Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
Yinlam Chow*, Stanford; Aviv Tamar, Technion; Marco Pavone, Stanford University; Shie Mannor, Technion

Asynchronous stochastic approximation: the noise is in the noise and SGD don't care
Sorathan Chaturapruek*, Stanford University; John Duchi, Stanford; Christopher Re,

Lifelong Learning with Non-i.i.d. Tasks
Anastasia Pentina*, IST Austria; Christoph Lampert, Institute of Science and Technology Austria

Optimal Linear Estimation under Unknown Nonlinear Transform
Xinyang Yi*, Utaustin; Zhaoran Wang, Princeton University; Constantine Caramanis, UT Austin; Han Liu, Princeton University

Learning with Group Invariant Features: A Kernel Perspective.
Youssef Mroueh*, IBM; Stephen Voinea, MIT; Tomaso Poggio, MIT

Regularized EM Algorithms: A Unified Framework and Statistical Guarantees
Xinyang Yi*, Utaustin; Constantine Caramanis, UT Austin

Distributionally Robust Logistic Regression
Soroosh Shafieezadeh Abadeh*, EPFL; Peyman Mohajerin Esfahani, EPFL; Daniel Kuhn, ?cole Polytechnique F?d?rale de Lausanne (EPFL)

Adaptive Stochastic Optimization: From Sets to Paths
Zhan Wei Lim*, NUS; David Hsu, National University of Singapore; Wee Sun Lee, National University of Singapore

Beyond Convexity: Stochastic Quasi-Convex Optimization
Elad Hazan, Princeton University; Kfir Levy*, Technion; Shai Shalev-Shwartz, Hebrew University

An Analytically Tractable Bayesian Approximation to Optimal Point Process Filtering
Yuval Harel*, Technion; Ron Meir, Technion; Manfred Opper, TU Berlin

Sum-of-Squares Lower Bounds for Sparse PCA
Tengyu Ma*, Princeton University; Avi Wigderson, Institute for Advanced Study

Max-Margin Majority Voting for Learning from Crowds
Tian Tian*, Tsinghua University; Jun Zhu, Tsinghua University

Learning with Incremental Iterative Regularization
Lorenzo Rosasco*, University of Genova; Silvia Villa, IIT-MIT

Halting in graph kernels
Mahito Sugiyama, Osaka University; Karsten Borgwardt*, ETH Zurich

MCMC for Variationally Sparse Gaussian Processes
James Hensman*, The University of Sheffield; Alex Matthews, Cambridge University; Maurizio Filippone, University of Glasgow; Zoubin Ghahramani, University of Cambridge

Less is More: Nystr\"om Computational Regularization
Lorenzo Rosasco*, University of Genova; Alessandro Rudi, ; Raffaello Camoriano, IIT - UNIGE

Infinite Factorial Dynamical Model
Isabel Valera*, MPI-SWS; Francisco Ruiz, University Carlos III, Madrid; Lennart Svensson, Chalmers University of Technology, Göteborg; Fernando Perez-Cruz,

Regularization Path of Cross-Validation Error Lower Bounds
Atsushi Shibagaki, Nagoya Institute of Technology; Yoshiki Suzuki, Nagoya Institute of Technology; Masayuki Karasuyama, Nagoya Institute of Technology; Ichiro Takeuchi*, Nagoya Institute of Technology

Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze–like Environments
Dane Corneil*, EPFL; Wulfram Gerstner, EPFL

Teaching Machines to Read and Comprehend
Karl Moritz Hermann*, Google DeepMind; Tomas Kocisky, Oxford University; Edward Grefenstette, Google DeepMind; Lasse Espeholt, Google DeepMind; Will Kay, Google DeepMind; Mustafa Suleyman, Google DeepMind; Phil Blunsom, Google DeepMind

Principal Differences Analysis: Interpretable Characterization of Differences between Distributions
Jonas Mueller*, MIT; Tommi Jaakkola, MIT

When are Kalman-Filter Restless Bandits Indexable?
Christopher Dance*, Xerox Research Centre Europe; Tomi Silander, Xerox Research Centre Europe

Segregated Graphs and Marginals of Chain Graph Models
Ilya Shpitser*, University of Southampton

Efficient Non-greedy Optimization of Decision Trees and Forests
Mohammad Norouzi, University of Toronto; Maxwell Collins*, UW-Madison; Matthew Johnson, Microsoft Research; David Fleet, University of Toronto; Pushmeet Kohli, Microsoft Research

Probabilistic Curve Learning: Coulomb Repulsion and the Electrostatic Gaussian Process
Ye Wang*, Duke Univiersity; David Dunson, Duke University

Inverse Reinforcement Learning with Locally Consistent Reward Functions
Quoc Phong Nguyen, National University of Singapore; Bryan Kian Hsiang Low*, National University of Singapore; Patrick Jaillet, Massachusetts Institute of Technology

Communication Complexity of Distributed Convex Learning and Optimization
Yossi Arjevani*, Weizmanninstitute; Ohad Shamir, The Weizmann Institute

End-to-end Learning of Latent Dirichlet Allocation by Mirror-Descent Back Propagation
Jianshu Chen*, Microsoft Research, Redmond, W; Ji He, University Washington; Yelong Shen, Microsoft Research, Redmond, WA; Lin Xiao, Microsoft; Xiaodong He, Microsoft Research, Redmond, WA; Jianfeng Gao, Microsoft Research, Redmond, WA; Xinying Song, Microsoft Research, Redmond, WA; Deng Li, MSR

Subset Selection by Pareto Optimization
Chao Qian*, Nanjing University; Yang Yu, Nanjing University; Zhi-Hua Zhou, Nanjing University

On the accuracy of self-normalized linear models
Maxim Rabinovich*, UC Berkeley; Jacob Andreas, UC Berkeley; Dan Klein, UC Berkeley; Michael Jordan, UC Berkeley

Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring
Junpei Komiyama*, The University of Tokyo; Junya Honda, The University of Tokyo; Hiroshi Nakagawa, The University of Tokyo

Is Approval Voting Optimal Given Approval Votes?
Ariel Procaccia*, Carnegie Mellon University; Nisarg Shah, Carnegie Mellon University

Regressive Virtual Metric Learning
Michaël Perrot*, Université de Saint-Etienne; Amaury Habrard,

Analysis of Robust PCA via Local Incoherence
Huishuai Zhang*, Syracuse University; Yi Zhou, Syracuse University; Yingbin Liang, Syracuse Univeristy

Learning to Transduce with Unbounded Memory
Edward Grefenstette*, Google DeepMind; Karl Moritz Hermann, Google DeepMind; Mustafa Suleyman, Google DeepMind; Phil Blunsom, Google DeepMind

Max-Margin Deep Generative Models
Chongxuan Li*, Tsinghua University; Jun Zhu, Tsinghua University; Tianlin Shi, Tsinghua University; Bo Zhang, Tsinghua University

Spherical Random Features for Polynomial Kernels
Jeffrey Pennington*, Google; Felix Yu, Columbia University; Sanjiv Kumar, Google

Rectified Factor Networks
Djork-Arné Clevert*, Johannes Kepler University; Andreas Mayr, Johannes Kepler University Linz; Thomas Unterthiner, Johannes Kepler University Linz; Sepp Hochreiter, Johannes Kepler University Linz

Learning Bayesian Networks with Thousands of Variables
Mauro Scanagattta*, IDSIA; Cassio de Campos, Queen's University Belfast; Giorgio Corani, IDSIA; Marco Zaffalon, IDSIA

Matrix Completion Under Monotonic Single Index Models
Ravi Ganti*, UW Madison; Rebecca Willett, University of Wisconsin

Visalogy: Answering Visual Analogy Questions
Fereshteh Sadeghi*, University of Washington; Ross Girshick, Microsoft Research; Larry Zitnick, Microsoft Research; Ali Farhadi, University of Washington

Tree-Guided MCMC Inference for Normalized Random Measure Mixture Models
Juho Lee*, POSTECH; Seungjin Choi, POSTECH

Streaming Min-max Hypergraph Partitioning
Jennifer Iglesias*, Carnegie Mellon University; Dan Alistarh, Microsoft Research; Milan Vojnovic, Microsoft Research

Collaboratively Learning Preferences from Ordinal Data
Sewoong Oh*, UIUC; Kiran Thekumparampil, UIUC; Jiaming Xu,

Biologically Inspired Dynamic Textures for Probing Motion Perception
Jonathan Vacher*, Université Paris Dauphine; Laurant Perrinet, Institut des neurosciences de la Timone; Andrew Meso, Institut des neurosciences de la Timone; Gabriel Peyré, Ceremade

Generative Image Modeling Using Spatial LSTMs
Lucas Theis*, U.Tuebingen; Matthias Bethge, CIN, University Tübingen

Robust PCA with compressed data
Wooseok Ha*, The University of Chicago; Rina Foygel Barber, University of Chicago

Sampling from Probabilistic Submodular Models
Alkis Gotovos*, ETH Zurich; Hamed Hassani, ETH Zurich; Andreas Krause, ETH

COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
Mehrdad Farajtabar*, Georgia Tech; Manuel Gomez Rodriguez, MPI SWS; Yichen Wang, Georgia Institute of Technology; Shuang Li, Georgia Institute of Technology; Hongyuan Zha, Georgia Tech; Le Song, Georgia Institute of Technology

On Predictive Belief Methods for Dynamical System Learning
Ahmed Hefny*, Carnegie Mellon University; Carlton Downey, Carnegie Mellon UNiversity; Geoff Gordon, CMU

Regret-Based Pruning in Extensive-Form Games
Noam Brown*, Carnegie Mellon University; Tuomas Sandholm, Carnegie Mellon University

Fast Two-Sample Testing with Analytic Representations of Probability Measures
Kacper Chwialkowski*, University College London; Arthur Gretton, University Collage London; Dino Sejdinovic, University of Oxford; Aaditya Ramdas, Carnegie Mellon University

Learning to Segment Object Candidates
Pedro Pinheiro*, EPFL; Ronan Collobert, Facebook; Piotr Dollar, Facebook AI Research

GP Kernels for Cross-Spectrum Analysis
Kyle Ulrich*, Duke; David Carlson, ; Lawrence Carin, Duke University

Secure Multi-party Differential Privacy
Peter Kairouz, UIUC; Sewoong Oh*, UIUC; Pramod Viswanath, UIUC

Spatial Transformer Networks
Max Jaderberg*, Google; Karen Simonyan, Google DeepMind; Andrew Zisserman, Google; Koray Kavukcuoglu, Google DeepMind

Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks
Kevin Scaman*, ENS Cachan - CMLA; Rémi Lemonnier, ENS Cachan - CMLA; Nicolas Vayatis, ENS Cachan - CMLA

Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms
Yunwen Lei*, City University of Hong Kong; Urun Dogan, Microsoft; Alexander Binder, ; Marius Kloft, Humboldt University Berlin

High-dimensional neural spike train analysis with generalized count linear dynamical systems
Yuanjun Gao*, Columbia; Lars Busing, Columbia University; Krishna Shenoy, Stanford University; John Cunningham, University of Columbia

Learning with a Wasserstein Loss
Chiyuan Zhang*, MIT; Charlie Frogner, MIT; Hossein Mobahi, MIT; Mauricio Araya, Shell Intl. E&P Inc.; Tomaso Poggio, MIT

b-bit Marginal Regression
Martin Slawski*, Rutgers University; Ping Li, Rugters University

Natural Neural Networks
Guillaume Desjardins*, Google DeepMind; Karen Simonyan, Google DeepMind; Razvan Pascanu, Google DeepMind; Koray Kavukcuoglu, Google DeepMind

Optimization Monte Carlo: Efficient and Embarrassingly Parallel Likelihood-Free Inference
Ted Meeds*, U. Amsterdam; Max Welling, University of Amsterdam

Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing
Tom Goldstein*, University of Maryland; Min Li, Southeast University; Xiaoming Yuan , Hong Kong Baptist University

On some provably correct cases of variational inference for topic models
Pranjal Awasthi*, Princeton; Andrej Risteski, Princeton

Collaborative Filtering with Graph Information: Consistency and Scalable Methods
Nikhil Rao*, University of Texas at Austin; Hsiang-Fu Yu, U Texas; Inderjit Dhillon, University of Texas at Austin; Pradeep Ravikumar, University of Texas at Austin

Combinatorial Bandits Revisited
Richard Combes, Supelec; Marc Lelarge, INRIA - ENS; Alexandre Proutiere, ; Mohammad Sadegh Talebi*, KTH Royal Inst. of Technology

Stochastic Variational Information Maximisation
Shakir Mohamed*, Google DeepMind; Danilo Rezende, Google DeepMind

A Structural Smoothing Framework For Robust Graph Comparison
Pinar Yanardag*, Purdue University; S.V.N. Vishwanathan, UCSC

Competitive Distribution Estimation: Why is Good-Turing Good
Alon Orlitsky, University of California, San Diego; Ananda Theertha Suresh*, UCSD

Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction
Joseph Wang*, ; Kirill Trapeznikov, STR; Venkatesh Saligrama, Boston University

A hybrid sampler for Poisson-Kingman mixture models
Maria Lomeli*, Gatsby; Stefano Favaro, University of Turin and Collegio Carlo Alberto; Yee Whye Teh, University of Oxford

An Active Learning Framework using Sparse-Graph Codes for Sparse Polynomials and Graph Sketching
Xiao Li*, UC Berkeley; Kannan Ramchandran, UC Berkeley

Local Smoothness in Variance Reduced Optimization
Daniel Vainsencher*, Princeton University; Han Liu, Princeton University; Tong Zhang, Rutgers

Saliency, Scale and Information: Towards a Unifying Theory
Shafin Rahman, University of Manitoba; Neil Bruce*, University of Manitoba

Fighting Bandits with a New Kind of Smoothness
Jacob Abernethy, University of Michigan; Chansoo Lee*, University of Michigan Ann Arb; Ambuj Tewari, University of Michigan

Beyond Sub-Gaussian Measurements: High-Dimensional Structured Estimation with Sub-Exponential Designs
VIDYASHANKAR SIVAKUMAR*, UNIVERSITY OF MINNESOTA, TC; Arindam Banerjee, University of Minnesota; Pradeep Ravikumar, University of Texas at Austin

Spectral Norm Regularization of Orthonormal Representations for Graph Transduction
RAKESH SHIVANNA*, Google Inc.; Bibaswan Chatterjee, Indian Institute of Science; Raman Sankaran, Indian Institute of Science; Chiranjib Bhattacharyya, Indian Institute of Science; Francis Bach, INRIA - ENS

Neural Molecular Fingerprints
David Duvenaud*, Harvard; Dougal Maclaurin, Harvard University; Jorge Aguilera Iparraguirre, Harvard University; Rafael Gómez Bombarell, Harvard University; Timothy Hirzel, Harvard University; Alan Aspuru-Guzik, Harvard University; Ryan Adams, Harvard

Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications
Kai Wei*, ; Rishabh Iyer, "University of Washington, Seattle"; Shengjie Wang, University of Washington; Wenruo Bai, University of Washington; Jeff Bilmes, "University of Washington, Seattle"

Tractable Learning for Complex Probability Queries
Jessa Bekker*, KU Leuven; Guy Van den Broeck, ; Arthur Choi, ; Adnan Darwiche, UCLA; Jesse Davis, Katholieke Universiteit Leuven

StopWasting My Gradients: Practical SVRG
Reza Babanezhad Harikandeh*, UBC; Mohamed Osama Ahmed, ; Alim Virani, ; Mark Schmidt, University of British Columbia; Jakub Konečný,

Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction
Been Kim, MIT; Julie Shah, MIT; Finale Doshi-Velez*, Harvard

A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks
Cengiz Pehlevan*, Simons Center for Data Analysi; Dmitri Chklovskii, Simons Foundation

On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators
Changyou Chen*, Duke University; Nan Ding, Google; Lawrence Carin, Duke University

Sparsistent Estimation of Nonparametric Graphical Models
Siqi Sun*, Ttic; Mladen Kolar, University of Chicago; Jinbo Xu, Technological Institute at Chicago

Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question
Haoyuan Gao, Baidu; Junhua Mao, UCLA; Jie Zhou, Baidu; Zhiheng Huang, Baidu; Lei Wang, Baidu; Wei Xu*, Baidu

Neighborhood Watch: Stochastic Gradient Descent with Neighbors
Thomas Hofmann*, ETH Zurich; Aurelien Lucchi, ETH Zurich; Brian McWilliams, ETH Zurich

Sample Efficient Path Integral Control under Uncertainty
Yunpeng Pan*, Georgia Institute of Technolog; Evangelos Theodorou, Georgia Tech

Stochastic Expectation Propagation
Yingzhen Li*, University of Cambridge; Jose Miguel Hernandez-Lobato, Harvard; Richard Turner, neuroscience

Approximate MAP Inference in Continuous MRFs
Nicholas Ruozzi*, UTDallas

Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients
Bo Xie*, Georgia Tech; Yingyu Liang, Princeton University; Le Song, Georgia Institute of Technology

Generalization in Adaptive Data Analysis and Holdout Reuse
Cynthia Dwork, Microsoft Research; Vitaly Feldman*, ; Moritz Hardt, Google; Toniann Pitassi, University of Toronto; Omer Reingold, Samsung Research; Aaron Roth, University of Pennsylvania

Market Scoring Rules Act As Opinion Pools For Risk-Averse Agents
Mithun Chakraborty*, Washington Univ. in St. Louis; Sanmay Das, Washington University in St. Louis

Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent
Ian En-Hsu Yen*, University of Texas at Austin; Kai Zhong, UT Austin; Cho-Jui Hsieh, UTexas-Austin; Pradeep Ravikumar, University of Texas at Austin; Inderjit Dhillon, University of Texas at Austin

Training Very Deep Networks
Rupesh Srivastava*, IDSIA; Klaus Greff, IDSIA; J?rgen Schmidhuber,

Bayesian Active Model Selection with an Application to Automated Audiometry
Jacob Gardner, Cornell University; Gustavo Malkomes, Washington University in St. Louis; Roman Garnett*, Washington University in STL; Kilian Weinberger, Cornell University; Dennis Barbour, Washington University in St. Louis; John Cunningham, University of Columbia

A Linear-Time Particle Gibbs Sampler for Infinite Hidden Markov Models
Nilesh Tripuraneni*, Cambridge University; Shixiang Gu, ; Hong Ge, University of Cambridge; Zoubin Ghahramani, University of Cambridge

Learning spatiotemporal trajectories from manifold-valued longitudinal data
Jean-Baptiste SCHIRATTI*, Ecole Polytechnique; Stéphanie ALLASSONNIERE, Ecole Polytechnique; Olivier COLLIOT, Université Pierre et Marie Curie (UPMC); Stanley DURRLEMAN, INRIA

A Bayesian Framework for Modeling Confidence in Perceptual Decision Making
Koosha Khalvati*, University of Washington; Rajesh Rao, University of Washington

Path-SGD: Path-Normalized Optimization in Deep Neural Networks
Behnam Neyshabur*, TTI Chicago; Ruslan Salakhutdinov, University of Toronto; Nati Srebro, Toyota Technological Institute at Chicago

On the consistency theory of high dimensional variable screening
Xiangyu Wang*, Duke University; Chenlei Leng, ; David Dunson, Duke University

End-To-End Memory Networks
Sainbayar Sukhbaatar*, New York University; Arthur Szlam, Facebook; Jason Weston, Facebook AI Research; Rob Fergus, Facebook AI Research

Spectral Representations for Convolutional Neural Networks
Oren Rippel*, MIT; Jasper Snoek, Harvard; Ryan Adams, Harvard

Online Gradient Boosting
Alina Beygelzimer, Yahoo!; Elad Hazan, Princeton University; Satyen Kale*, Yahoo Labs; Haipeng Luo, Princeton University

Deep Temporal Sigmoid Belief Networks for Sequence Modeling
Zhe Gan*, Duke University; Chunyuan Li, Duke University; Ricardo Henao, Duke University; David Carlson, ; Lawrence Carin, Duke University

Recognizing retinal ganglion cells in the dark
Emile Richard*, Institut Curie; Georges Goetz, Stanford University; EJ Chichilnisky, Stanford

A Theory of Decision Making Under Dynamic Context
Michael Shvartsman*, Princeton Neuroscience Inst.; Vaibhav Srivastava, Princeton Neuroscience Institute; Jonathan Cohen, Princeton University

A Gaussian Process Model of Quasar Spectral Energy Distributions
Andrew Miller*, Harvard; Albert Wu, Harvard; Ryan Adams, Harvard

Hidden Technical Debt in Machine Learning Systems
D Sculley*, Google Research; Gary Holt, ; Daniel Golovin, Google, Inc.; Eugene Davydov, Google, Inc.; Todd Phillips, Google, Inc.; Dietmar Ebner, ; Vinay Chaudhary, Google, Inc.; Michael Young, Google, Inc.; Jean-Francois Crespo, Google, Inc.; Dan Dennison, Google, Inc.

Local Causal Discovery
Tian Gao*, RPI; Qiang Ji,

High Dimensional EM Algorithm: Statistical Optimization and Asymptotic Normality
Zhaoran Wang*, Princeton University; Quanquan Gu, University of Virginia; Yang Ning, Princeton University; Han Liu, Princeton University

Revenue Optimization against Strategic Buyers
Andres Munoz Medina*, Courant Institute of Mathematical Sciences; Mehryar Mohri, Courant Institute and Google

Deep Convolutional Inverse Graphics Network
Pushmeet Kohli, Microsoft Research; Will Whitney, MIT; Tejas Kulkarni*, MIT; Josh Tenenbaum, MIT

Sparse and Low-Rank Tensor Decomposition
Parikshit Shah*, Yahoo Labs; Nikhil Rao, University of Texas at Austin; Gongguo Tang, Coloradoschoolofmines

Minimax Time Series Prediction
Wouter Koolen*, Queensland University of Technology; Alan Malek, UC Berkeley; Peter Bartlett, UC Berkeley; Yasin Abbasi-Yadkori, Queensland University of Technology

Differentially Private Learning of Structured Discrete Distributions
Ilias Diakonikolas, University of Edinburgh; Moritz Hardt, Google; Ludwig Schmidt*,

Variational Dropout and the Local Reparameterization Trick
Diederik Kingma*, U. Amsterdam; Tim Saliman, Algorithmica; Max Welling, University of Amsterdam

Sample Complexity of Learning Mahalanobis Distance Metrics
Nakul Verma*, Janelia Research Campus HHMI; Kristin Branson, Janelia Research Campus, HHMI

Learning Wake-Sleep Recurrent Attention Models
Jimmy Ba*, University of Toronto; Ruslan Salakhutdinov, University of Toronto; Roger Grosse, University of Toronto; Brendan Frey, U. Toronto

Robust Gaussian Graphical Modeling with the Trimmed Graphical Lasso
Eunho Yang*, IBM Thomas J. Watson Research Center; Aurelie Lozano, IBM Research

Testing Closeness With Unequal Sized Samples
Bhaswar Bhattacharya*, Stanford University; Greg Valiant, Stanford University

Estimating Jaccard Index with Missing Observations: A Matrix Calibration Approach
Wenye Li*, Macao Polytechnic Institute

Neural Adaptive Sequential Monte Carlo
Shixiang Gu*, ; Richard Turner, neuroscience; Zoubin Ghahramani, University of Cambridge

Local Expectation Gradients for Doubly Stochastic Variational Inference
Michalis Titsias, Athens University of Economics and Business; Miguel Lázaro Gredilla*, Vicarious

On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
Sashank J Reddi*, Carnegie Mellon University; Ahmed Hefny, Carnegie Mellon University; Suvrit Sra, MIT; Barnabas Poczos, Carnegie Mellon University; Alex Smola, Carnegie Mellon University

NEXT: A System for Real-World Development, Evaluation, and Application of Active Learning
Kevin Jamieson*, University of Wisconsin; Lalit Jain, University of Wisconsin; Chris Fernandez, University of Wisconsin; Nicholas Glattard, University of Wisconsin; Rob Nowak, Wisconsin

Super-Resolution Off the Grid
Qingqing Huang, MIT; Sham Kakade*, University of Washington

Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms
Christopher De Sa*, Stanford; Ce Zhang, Wisconsin; Kunle Olukotun, Stanford; Christopher Ré, Stanford

The Return of the Gating Network: combining generative models and discriminative training in natural image priors.
Dan Rosenbaum*, The Hebrew University; Yair Weiss, Hebrew University

Pointer Networks
Oriol Vinyals*, Google; Meire Fortunato, ; Navdeep Jaitly, Google

Associative Memory via a Sparse Recovery Model
Ankit Singh Rawat*, University of Texas at Austin; Arya Mazumdar, University of Minnesota -- Twin Cities

Robust Spectral Inference for Joint Stochastic Matrix Factorization
Moontae Lee*, Cornell University; David Mimno, Cornell University; David Bindel, Cornell University

Fast, Provable Algorithms for Isotonic Regression in all l_p-norms
Sushant Sachdeva*, Yale University; Anup Rao, Yale University; Rasmus Kyng, Yale University

Structured Prediction Games for Multivariate Losses
Hong Wang*, University of Illinois at Chic; Wei Xing, University of Illinois at Chicago; Kaiser Asif, University of Illinois at Chicago; Brian Ziebart, University of Illinois at Chic

Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization
Xiangru Lian, University of Rochester; Ji Liu*, University of Rochester; Yijun Huang, University of Rochester; Yuncheng Li, University of Rochester

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
Manuel Watter, University of Freiburg; Jost Springenberg*, University of Freiburg; Joschka Boedecker, University of Freiburg; Martin Riedmiller, University of Freiburg

Efficient and Parsimonious Agnostic Active Learning
Tzu-Kuo Huang*, Microsoft; Alekh Agarwal, Microsoft Research; Daniel Hsu, Columbia University; John Langford, Microsoft Research New York; Robert Schapire, MIcrosoft Research

Softstar: Softened Heuristic-based Inference
Mathew Monfort*, ; Josh Tenenbaum, MIT; Brian Ziebart, University of Illinois at Chic; Patrick Lucey, Disney Research Pittsburgh; Brenden Lake, MIT

Grammar as a Foreign Language
Oriol Vinyals*, Google; Lukasz Kaiser, Google; Terry Koo, Google; Slav Petrov, Google; Ilya Sutskever, Google; Geoffrey Hinton, Google

Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices
Martin Slawski*, Rutgers University; Ping Li, Rugters University; Matthias Hein, Saarland University

Winner-Take-All Autoencoders
Alireza Makhzani*, University of Toronto; Brendan Frey, U. Toronto

Deep Poisson Factor Modeling
Ricardo Henao*, Duke University; Zhe Gan, Duke University; James Lu, Duke University; Lawrence Carin, Duke University

Bayesian Optimization with Exponential Convergence
Kenji Kawaguchi*, MIT; Leslie Kaelbling, MIT; Tomás Lozano-Pérez,

Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning
Christoph Dann*, CMU; Emma Brunskill, CMU

Learning with Relaxed Supervision
Jacob Steinhardt*, Stanford University; Percy Liang, Stanford University

Subsampled Power Iteration: a Unified Algorithm for Block Models and Planted CSP's
Vitaly Feldman, ; Will Perkins*, University of Birmingham; Santosh Vempala, Georgia Tech

Accelerated Mirror Descent in Continuous and Discrete Time
Walid Krichene*, UC Berkeley; Alexandre Bayen, UC Berkeley; Peter Bartlett, UC Berkeley

The Human Kernel
Andrew Wilson*, Carnegie Mellon University; Christoph Dann, CMU; Chris Lucas, University of Edinburgh; Eric Xing, Carnegie Mellon University

Action-Conditional Video Prediction using Deep Networks in Atari Games
Junhyuk Oh*, University of Michigan; Xiaoxiao Guo, Uni; Honglak Lee, U. Michigan; Satinder Singh, University of Michigan; Richard Lewis, University of Michigan

A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA
James Voss, ; Mikhail Belkin, Ohio State University; Luis Rademacher*, The Ohio State University

Distributed Submodular Cover: Succinctly Summarizing Massive Data
Baharan Mirzasoleiman*, ETHZ; Amin Karbasi, Yale; Ashwinkumar Badanidiyuru, Google; Andreas Krause, ETHZ

Community Detection via Measure Space Embedding
Mark Kozdoba*, Technion; Shie Mannor, Technion

Basis refinement strategies for linear value function approximation in MDPs
Gheorghe Comanici*, McGill University, Montreal; Doina Precup, University of McGill; Prakash Panangaden, McGill University, Montreal

Structured Estimation with Atomic Norms: General Bounds and Applications
Sheng Chen*, University of Minnesota; Arindam Banerjee, University of Minnesota

A Complete Recipe for Stochastic Gradient MCMC
Yi-An Ma*, University of Washington; Tianqi Chen, University of Washington; Emily Fox, Washington

Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff
Ofer Dekel*, Microsoft Research; Tomer Koren, Technion

Online Prediction at the Limit of Zero Temperature
Mark Herbster*, University College London; Stephen Pasteris, UCL; Shaona Ghosh, University of Southhampton

Learning Continuous Control Policies by Stochastic Value Gradients
Nicolas Heess, Google DeepMind; Greg Wayne*, Google DeepMind; David Silver, DeepMind; Timothy Lillicrap, Google DeepMind; Tom Erez, Google DeepMind; Yuval Tassa, Google DeepMind

Exploring Models and Data for Image Question Answering
Mengye Ren*, University of Toronto; Ryan Kiros, U. Toronto; Richard Zemel, University of Toronto

Efficient and Robust Automated Machine Learning
Matthias Feurer, University of Freiburg; Aaron Klein*, University of Freiburg; Katharina Eggensperger, University of Freiburg; Jost Springenberg, University of Freiburg; Manuel Blum, University of Freiburg; Frank Hutter, U Freiburg

Preconditioned Spectral Descent for Deep Learning
David Carlson*, ; Edo Collins, ; Ya-Ping Hsieh, EPFL; Lawrence Carin, Duke University; Volkan Cevher, EPFL

A Recurrent Latent Variable Model for Sequential Data
Junyoung Chung*, University of Montreal; Kyle Kastner, Universite de Montreal; Viet Hanh Laurent Dinh, University of Montreal; Kratarth Goel, University of Montreal; Aaron Courville, U. Montreal; Yoshua Bengio, U. Montreal

Fast Convergence of Regularized Learning in Games
Vasilis Syrgkanis, Microsoft Research; Alekh Agarwal*, Microsoft Research; Haipeng Luo, Princeton University; Robert Schapire, MIcrosoft Research

Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Marijn Stollenga*, IDSIA; Wonmin Byeon, IDSIA  Marcus Liwicki, TU Kaiserslautern; J?rgen Schmidhuber, 

Reflection, Refraction, and Hamiltonian Monte Carlo
Hadi Mohasel Afshar*, Australian National University; Justin Domke, NICTA

The Consistency of Common Neighbors for Link Prediction in Stochastic Blockmodels
Purnamrita Sarkar*, UT Austin; Deepayan Chakrabarti, UT Austin; Peter Bickel, U C Berkeley

Nearly Optimal Private LASSO
Kunal Talwar*, Google; Li Zhang, Google; Abhradeep Thakurta,

Convergence Analysis of Prediction Markets via Randomized Subspace Descent
Rafael Frongillo*, Harvard University; Mark Reid, Australia National University

The Poisson Gamma Belief Network
Mingyuan Zhou*, University of Texas at Austin; Yulai Cong, ; Bo Chen, Xidian University

Convergence rates of sub-sampled Newton methods
Murat Erdogdu*, Stanford University; Andrea Montanari, Stanford

No-Regret Learning in Repeated Bayesian Games
Jason Hartline, Northwestern University; Vasilis Syrgkanis*, Microsoft Research; Eva Tardos, Cornell University

Statistical Topological Data Analysis - A Kernel Perspective
Roland Kwitt*, University of Salzburg; Ulrich Bauer, TU Munich; Stefan Huber, IST Austria; Marc Niethammer, UNC Chapel Hill; Weili Lin, UNC Chapel Hill

Unsupervised Sequence Learning
Andrew Dai*, Google Inc; Quoc Le, Google

Structured Transforms for Small-Footprint Deep Learning
Vikas Sindhwani*, Google; Tara Sainath, Google; Sanjiv Kumar, Google

Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width
Christopher De Sa*, Stanford; Ce Zhang, Wisconsin; Kunle Olukotun, Stanford; Christopher Ré, Stanford

Interpolating Convex and Non-Convex Tensor Decompositions via the Subspace Norm
Qinqing Zheng, University of Chicago; Ryota Tomioka*, Toyota Technological Institute at Chicago

Sample Complexity Bounds for Iterative Stochastic Policy Optimization
Marin Kobilarov*, Johns Hopkins University

BinaryConnect: Training Deep Neural Networks with binary weights during propagations
Matthieu Courbariaux*, École Polytechnique Montréal; Yoshua Bengio, U. Montreal; Jean-Pierre David, Polytechnique Montréal

Interactive Control of Diverse Complex Characters with Neural Networks
Igor Mordatch*, University of Washington; Kendall Lowrey, University of Washington; Galen Andrew, """University of Washington, Seattle"""; Zoran Popović, University of Washington; Emanuel Todorov, University of Washington

Submodular Hamming Metrics
Jennifer Gillenwater*, University of Pennsylvania; Rishabh Iyer, "University of Washington, Seattle"; Bethany Lusch, University of Washington; Rahul Kidambi, University of Washington; Jeff Bilmes, "University of Washington, Seattle"

A universal primal-dual convex optimization framework
Alp Yurtsever, LIONS, EPFL, Lausanne; Quoc Tran Dinh*, LIONS, EPFL, Lausanne; Volkan Cevher, EPFL

Learning-curve analysis of simple decision heuristics
Ozgur Simsek*, Max Plank Institute Berlin; Marcus Buckmann, Max Planck Institute

Explore no more: improved high-probability regret bounds for non-stochastic bandits
Gergely Neu*, INRIA

Fast and Memory Optimal Low-Rank Matrix Approximation
Seyoung Yun*, MSR-INRIA; Marc Lelarge, INRIA - ENS; Alexandre Proutiere,

Learnability of Influence in Networks
Harikrishna Narasimhan*, Indian Institute of Science; David Parkes, Harvard University ; Yaron Singer, Harvard University

Learning Causal Graphs with Small Interventions
Karthikeyan Shanmugam, UT Austin; Murat Kocaoglu*, UT Austin; Alex Dimakis, Utaustin

Information-theoretic lower bounds for convex optimization with erroneous oracles
Yaron Singer*, Harvard University; Jan Vondrak, IBM Research

Fixed-Length Poisson MRF: Adding Dependencies to the Multinomial
David Inouye*, University of Texas at Austin; Pradeep Ravikumar, University of Texas at Austin; Inderjit Dhillon, University of Texas at Austin

Large-Scale Bayesian Multi-Label Learning via Positive Labels Only
Piyush Rai*, Duke University; Changwei Hu, ; Ricardo Henao, Duke University; Lawrence Carin, Duke University

The Self-Normalized Estimator for Counterfactual Learning
Adith Swaminathan*, Cornell University; Thorsten Joachims, Cornell

Fast Lifted MAP Inference via Partitioning
Somdeb Sarkhel*, University of Texas at Dallas; Parag Singla, Indian Institute of Technology; Vibhav Gogate, UT Dallas

Data Generation as Sequential Decision Making
Philip Bachman*, McGill University; Doina Precup, University of McGill

On Elicitation Complexity and Conditional Elicitation
Rafael Frongillo*, Harvard University; Ian Kash, Microsoft

Decomposition Bounds for Marginal MAP
Wei Ping*, UC Irvine; Qiang Liu, MIT; alexander ihler, UC irvine

Inference and Feature Selection via Maximal Correlation
Meisam Razaviyayn*, Stanford University; Farzan Farnia, ; David Tse,

A class of network models recoverable by spectral clustering
Yali Wan*, University of Washington; Marina Meila, University of Washington

Skip-Thought Vectors
Ryan Kiros*, U. Toronto; Yukun Zhu, University of Toronto; Ruslan Salakhutdinov, University of Toronto; Richard Zemel, University of Toronto; Raquel Urtasun, University of Toronto; Antonio Torralba, MIT; Sanja Fidler, University of Toronto

Rate-Agnostic (Causal) Structure Learning
Sergey Plis*, The Mind Research Network; David Danks, Carnegie Mellon University; Cynthia Freeman, The Mind Research Network; Vince Calhoun, MRN

Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric
Vivien Seguy*, Kyoto University; Marco Cuturi, Kyoto University

Consistent Multilabel Classification
Sanmi Koyejo*, Stanford University; Nagarajan Natarajan, UT Austin; Pradeep Ravikumar, University of Texas at Austin; Inderjit Dhillon, University of Texas at Austin

Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions
Amar Shah*, Cambridge; Zoubin Ghahramani, University of Cambridge

Cornering Stationary and Restless Mixing Bandits with Remix-UCB
Julien Audiffren*, CMLA, ENS Cachan; Liva Ralaivola, Univesity of Marseille

Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data
Danilo Bzdok*, INRIA; Michael Eickenberg, ; Olivier Grisel, ; Bertrand Thirion, INRIA; Gael Varoquaux, Parietal Team, INRIA

Gaussian Process Random Fields
David Moore*, UC Berkeley; Stuart Russell, UC Berkeley

M-Statistic for Kernel Change-Point Detection
Shuang Li, Georgia Institute of Technology; Yao Xie*, Georgia Tech; Hanjun Dai, Georgia Tech; Le Song, Georgia Institute of Technology

Adaptive Online Learning
Dylan Foster*, Cornell University; Alexander Rakhlin, UPenn; Karthik Sridharan, Cornell

A Universal Catalyst for First-Order Optimization
Hongzhou Lin, Inria; Julien Mairal*, INRIA; Zaid Harchaoui, Inria

Inference for determinantal point processes without spectral knowledge
Michalis Titsias, Athens University of Economics and Business; Remi Bardenet*, University of Lille

Kullback-Leibler Proximal Variational Inference
Mohammad Emtiyaz Khan*, EPFL

Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization
Niao He, Georgiatech; Zaid Harchaoui*, Inria

LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements
Christos Thrampoulidis*, Caltech; Ehsan Abbasi, Caltech; Babak Hassibi, Caltech

From random walks to distances on unweighted graphs
Tatsunori Hashimoto*, MIT CSAIL; Yi Sun, MIT Mathematics; Tommi Jaakkola, MIT

Bayesian dark knowledge
Anoop Korattikara*, Google; Vivek Rathod, Google; Kevin Murphy, Google; Max Welling,

Matrix Completion with Noisy Side Information
Kai-Yang Chiang*, UT Austin; Cho-Jui Hsieh, UTexas-Austin; Inderjit Dhillon, University of Texas at Austin

Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation
Scott Linderman*, Harvard Unviersity; Matthew Johnson, MIT; Ryan Adams, Harvard

On-the-Job Learning with Bayesian Decision Theory
Keenon Werling*, Stanford University; Arun Chaganty, Stanford; percy Liang, Stanford University

Calibrated Structured Prediction
Volodymyr Kuleshov*, Stanford University; percy Liang, Stanford University

Learning Structured Output Representation using Deep Conditional Generative Models
Kihyuk Sohn*, University of Michigan; Honglak Lee, U. Michigan; Xinchen Yan, UMich

Time-Sensitive Recommendation From Recurrent User Activities
Nan Du*, ; yichen wang, ; Le Song, Georgia Institute of Technology

Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels
Felipe Tobar*, University of Cambridge; Thang Bui, University of Cambridge; Richard Turner, neuroscience

Eliciting and Aggregating Private Information
Jacob Abernethy, University of Michigan; Rafael Frongillo, Harvard University; Bo Waggoner*, Harvard

Lifted Inference Rules With Constraints
Happy Mittal*, IIT Delhi; Anuj Mahajan, ; Vibhav Gogate, UT Dallas; Parag Singla, Indian Institute of Technology

Gradient Estimation Using Stochastic Computation Graphs
John Schulman*, UC Berkeley / Google; Nicolas Heess, Google DeepMind; Theophane Weber, Google DeepMind; Pieter Abbeel, UC Berkeley

Model-Based Relative Entropy Stochastic Search
Abbas Abdolmaleki*, University of aveiro; Jan Peters, TU Darmstadt; Gerhard Neumann,

Semi-supervised Learning with Ladder Network
Antti Rasmus*, Aalto University; Mathias Berglund, Aalto University; Mikko Honkala, Nokia Labs; Harri Valpola, ZenRobotics; Tapani Raiko, Aalto University

Embedding Inference for Structured Multilabel Prediction
Farzaneh Mirzazadeh, University of Alberta; Siamak Ravanbakhsh, University of Alberta; Bing Xu, University of Alberta; Nan Ding, Google; Dale Schuurmans*, Alberta

Variational inference with copula augmentation
Dustin Tran*, Harvard University; David Blei, Columbia University; Edoardo Airoldi, Harvard University

Recursive 2D-3D Convolutional Networks for Neuronal Boundary Prediction
Kisuk Lee*, MIT; Aleksandar Zlateski, MIT; Vishwanathan Ashwin, Princeton University; H. Sebastian Seung, Princeton University

A Dual-Augmented Block Minimization Framework for Learning with Limited Memory
Ian En-Hsu Yen*, University of Texas at Austin; Shan-Wei Lin, National Taiwan University; Shou-De Lin, National Taiwan University

Optimal Testing for Families of Distributions
Jayadev Acharya, Massachusetts Institute of Technology; Constantinos Daskalakis*, MIT; Gautam Kamath, MIT

Efficient Continuous-Time Hidden Markov Model for Disease Modeling
Yu-Ying Liu*, Georgia Tech; Le Song, Georgia Institute of Technology; Fuxin Li, Georgia Tech; Shuang Li, Georgia Tech; James Rehg, Georgia Tech

Expectation Particle Belief Propagation
Thibaut Lienart*, University of Oxford; Yee Whye Teh, University of Oxford; Arnaud Doucet, Oxford

Latent Bayesian melding for integrating individual and population models
Mingjun Zhong*, University of Edinburgh; Nigel Goddard, ; Charles Sutton, University of Edinburgh