AISTATS 2019 Accepted Papers

  • Proximal Splitting Meets Variance Reduction
    Fabian Pedregosa (UC Berkeley)*; Kilian EJ Fatras (ENSTA ParisTech); Mattia Casotto (Kamet)
  • Optimal Noise-Adding Mechanism in Additive Differential Privacy
    Quan Geng (Google)*; Wei Ding (Google); Ruiqi Guo (Google); Sanjiv Kumar (Google Research)
  • Tossing Coins Under Monotonicity
    Matey Neykov (Carnegie Mellon University)*
  • Gaussian Regression with Convex Constraints
    Matey Neykov (Carnegie Mellon University)*
  • Risk-Averse Stochastic Convex Bandit
    Adrian Rivera Cardoso (Georgia Tech)*; Huan Xu (Georgia Inst. of Technology)
  • Error bounds for sparse classifiers in high-dimensions
    Antoine Dedieu (MIT)*
  • Boosting Survival Predictions with Auxiliary Data from Heterogeneous Domains
    Alexis Bellot (University of Oxford)*
  • Resampled Priors for Variational Autoencoders
    Matthias Bauer (MPI Intelligent Systems/University of Cambridge)*; Andriy Mnih (DeepMind)
  • Scalable Bayesian Learning for State Space Models using Variational Inference with SMC Samplers
    Marcel Hirt (University College London)*; Petros Dellaportas (UCL)
  • Scalable Thompson Sampling via Optimal Transport
    Ruiyi Zhang (Duke University)*; Zheng Wen (Adobe Research); Changyou Chen (University at Buffalo); CHEN FANG (Adobe Research, San Jose, CA)
  • Inferring Multidimensional Rates of Aging from Cross-Sectional Data
    Emma Pierson (Stanford)*; Pang Wei Koh (Stanford); Tatsunori Hashimoto (Stanford); Daphne Koller (insitro); Jure Leskovec (Stanford); Nick Eriksson (Calico); Percy Liang ()
  • Interaction Detection with Bayesian Decision Tree Ensembles
    Junliang Du (Florida State University); Antonio R Linero (Florida State University)*
  • Interaction Effects: The Lurking Problem in Machine Learning Systems
    Matt Barnes (Carnegie Mellon University)*; Artur Dubrawski (CMU)
  • Towards a Theoretical Understanding of Hashing-Based Neural Nets
    Yibo Lin (UT-Austin)*; Zhao Song (Harvard University); Lin Yang (Princeton University)
  • Faster First-Order Methods for Stochastic Non-Convex Optimization on Riemannian Manifolds
    Pan Zhou (NUS)*; Jiashi Feng (NUS); Xiaotong Yuan (Nanjing University of Information Science and Technology)
  • A Low-Level Probabilistic Programming Language for Non-Differentiable Models
    Yuan Zhou (University of Oxford); Bradley J Gram-Hansen (University of Oxford)*; Tobias Kohn (University of Oxford); Tom Rainforth (University of Oxford); Frank Wood (University of British Columbia); Hongseok Yang ()
  • Learning Large-Scale Generalized Hypergeometric Distribution (GHD) DAG Models
    Gunwoong Park (University of Seoul)*; Hyewon Park (University of Seoul)
  • Unbiased Implicit Variational Inference
    Michalis Titsias (Athens University)*; Francisco Ruiz (Columbia University, University of Cambridge)
  • Efficient Linear Bandits through Matrix Sketching
    Ilja Kuzborskij (University of Milan)*; Leonardo Cella (); Nicolo A Cesa Bianchi (Milan University)
  • Orthogonal Estimation of Wasserstein Distances
    Mark Rowland (DeepMind)*; Jiri Hron (University of Cambridge); Krzysztof Choromanski (Google Brain Robotics); Tamas Sarlos (Google Research); Yunhao Tang (Columbia University); Adrian Weller (Cambridge University)
  • Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity
    Simon S Du (Carnegie Mellon University); Wei Hu (Princeton University)*
  • Weak-submodularity-based Greedy and IHT-style Algorithms for Non-convex Optimization with Monotone Costs of Non-zeros
    Shinsaku Sakaue (NTT)*
  • Block Stability for MAP Inference
    Hunter Lang (MIT)*; David Sontag (MIT); Aravindan Vijayaraghavan ()
  • A Stein--Papangelou Goodness-of-Fit Test for Point Processes
    Jiasen Yang (Purdue University)*; Vinayak Rao (Purdue University); Jennifer Neville (Purdue University)
  • KAMA-NNs: low-dimensional rotation based neural networks
    Krzysztof Choromanski (Google Brain Robotics)*; Aldo Pacchiano (UC Berkeley); Jeffrey Pennington (Google Brain); Yunhao Tang (Columbia University)
  • Statistical Windows in Testing for the Initial Distribution of a Reversible Markov Chain
    Quentin Berthet (University of Cambridge); Varun Kanade (Oxford)*
  • Sketching for Latent Dirichlet-Categorical Models
    Joseph Tassarotti (Carnegie-Mellon University)*; Jean-Baptiste Tristan (Oracle Labs); Michael Wick (Oracle Labs)
  • Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models
    Randy Ardywibowo (Texas A&M University)*; Guang Zhao (Texas A&M University); Zhangyang Wang (TAMU); Bobak J Mortazavi (Texas A&M University); Shuai Huang (University of Washington); Xiaoning Qian (Texas A&M University)
  • Near Optimal Algorithms for Hard Submodular Programs with Discounted Cooperative Costs
    Rishabh Krishnan Iyer (Microsoft Corporation)*; Jeffrey Bilmes (University of Washington)
  • Fast Stochastic Algorithms for Low-rank and Nonsmooth Matrix Problems
    Dan Garber (Technion)*; Atara Kaplan (Technion)
  • Logarithmic Regret for Online Gradient Descent Beyond Strong Convexity
    Dan Garber (Technion)*
  • Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches
    Filip Hanzely (KAUST)*; Peter Richtarik (KAUST)
  • Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems
    Bhaskar Mukhoty (Indian Institute of Technology Kanpur)*; Govind Gopakumar (Goldman Sachs); Prateek Jain (Microsoft Research); Purushottam Kar (Indian Institute of Technology Kanpur)
  • Modularity-based Sparse Soft Graph Clustering
    Alexandre Hollocou (INRIA, Paris)*; Thomas Bonald (Telecom Paristech); Marc Lelarge (INRIA-ENS)
  • Pathwise Derivatives for Multivariate Distributions
    Martin Jankowiak (Uber AI Labs)*; Theofanis Karaletsos (Uber AI Labs)
  • Distributed Inexact Newton-type Pursuit for Non-convex Sparse Learning
    Bo Liu (Rutgers University)*; Xiaotong Yuan (Nanjing University of Information Science and Technology); Lezi Wang (Rutgers Uniersity); Qingshan Liu (Nanjing University of Information Science & Technology); Junzhou Huang (University of Texas at Arlington); Dimitris Metaxas (Rutgers)
  • Vine copula structure learning via Monte Carlo tree search
    Bo Chang (University of British Columbia)*; Shenyi Pan (University of British Columbia); Harry Joe (University of British Columbia)
  • Blind Demixing via Wirtinger Flow with Random initialization
    Jialin Dong (ShanghaiTech University); Yuanming Shi (ShanghaiTech University)*
  • Performance Metric Elicitation from Pairwise Classifier Comparisons
    Gaurush Hiranandani (UNIVERSITY OF ILLINOIS, URBANA-CH)*; Shant Boodaghians (UIUC); Ruta Mehta (UIUC); Sanmi Koyejo (University of Illinois, Urbana-Champaign)
  • Analysis of Network Lasso for Semi-Supervised Regression
    Alexander Jung (Aalto University)*; Natalia Vesselinova (Aalto University)
  • Learning Mixtures of Smooth Product Distributions: Identifiability and Algorithm
    Nikolaos Kargas (UMN)*; Nicholas Sidiropoulos (University of Virginia)
  • Robust Low-Rank Estimation from Quantized Observations
    Jie Shen (Stevens Institute of Technology)*; Pranjal Awasthi (Rutgers University); Ping Li (Baidu Research)
  • Foundations of Sequence-to-Sequence Modeling for Time Series
    Zelda Mariet (Massachusetts Institute of Technology)*; Vitaly Kuznetsov (Google)
  • Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit
    Yang Cao (Uber Technologies, Inc)*; Zheng Wen (Adobe Research); Branislav Kveton (Google Research); Yao Xie (Georgia Tech)
  • An Optimal Algorithm for Stochastic Three-Composite Optimization
    Renbo Zhao (MIT)*; William Haskell (NUS); Vincent Tan (NUS)
  • Thompson Sampling for Cascading Bandits
    Wang Chi Cheung (IHPC, ASTAR); Vincent Tan (NUS); Zixin Zhong (NUS)*
  • Lifelong Optimization with Low Regret
    Yi-Shan Wu (Academia Sinica)*; Po-An Wang (LIONS, EPFL); Chi-Jen Lu (Academia Sinica)
  • Sparse Multivariate Bernoulli Processes in High Dimensions
    Parthe Pandit (University of California Los Angeles)*; Arash Amini (UCLA); Mojtaba Sahraee-Ardakan (UCLA); Sundeep Rangan (NYU); Alyson K Fletcher (UCLA)
  • An Optimal Algorithm for Stochastic and Adversarial Bandits
    Julian Zimmert (University of Copenhagen)*; Yevgeny Seldin (University of Copenhagen)
  • Efficient Bayesian Experimental Design for Implicit Models
    Steven Kleinegesse (University of Edinburgh)*; Michael U. Gutmann (University of Edinburgh)
  • Local Saddle Point Optimization: A Curvature Exploitation Approach
    Leonard Adolphs (ETHZ)*; Hadi Daneshmand (ETH); Aurelien Lucchi (ETH Zurich); Thomas Hofmann (ETH Zurich)
  • Testing Conditional Independence on Discrete Data using Stochastic Complexity
    Alexander Marx (Max-Planck-Institut for Informatics)*; Jilles Vreeken (CISPA Helmholtz Center for Information Security)
  • Distributionally Robust Submodular Maximization
    Matthew Staib (MIT)*; Bryan Wilder (University of Southern California); Stefanie Jegelka (MIT)
  • A Robust Zero-Sum Game Framework for Pool-based Active Learning
    Dixian Zhu (University of Iowa)*; Zhe Li (The University of Iowa ); Xiaoyu Wang (-); Boqing Gong (Tencent AI Lab); Tianbao Yang (University of Iowa)
  • Support and Invertibility in Domain-Invariant Representations
    Fredrik D Johansson (MIT)*; David Sontag (MIT); Rajesh Ranganath (New York University)
  • Efficient Inference in Multi-task Cox Process Models
    Virginia Aglietti (University of Warwick)*; Theodoros Damoulas (University of Warwick); Edwin V Bonilla (Data61)
  • Optimization of Inf-Convolution Regularized Nonconvex Composite Problems
    Emanuel Laude (TU Munich)*; Tao Wu (TU Munich); Daniel Cremers (TUM)
  • On Connecting Stochastic Gradient MCMC and Differential Privacy
    Bai Li (Duke University)*; Changyou Chen (University at Buffalo); Hao Liu (Nanjing University); Lawrence Carin Duke (CS)
  • What made you do this? Understanding black-box decisions with sufficient input subsets
    Brandon Carter (MIT CSAIL)*; Jonas Mueller (MIT); Siddhartha Jain (MIT CSAIL); David Gifford (MIT CSAIL)
  • Computation Efficient Coded Linear Transform
    Sinong Wang (The Ohio State University)*; Jiashang Liu (The Ohio State University); Ness Shroff (The Ohio State University); Pengyu Yang (The Ohio State University)
  • Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions 2: Numerical integrators
    Oren Mangoubi (EPFL)*; Aaron Smith (University of Ottawa)
  • Temporal Quilting for Survival Analysis
    Changhee Lee (UCLA)*; William Zame (UCLA); Ahmed M. Alaa (University of California, Los Angeles); Mihaela van der Schaar ()
  • Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms
    Mathieu Blondel (NTT)*; Andre Martins (Unbabel); Vlad Niculae (Instituto de Telecomunicações)
  • On Target Shift in Adversarial Domain Adaptation
    Yitong Li (Duke University)*; David Carlson (Duke)
  • Optimal testing in the experiment-rich regime
    Sven Schmit (Stitch Fix, Inc)*; Ramesh Johari (Stanford University); Virag Shah (Stanford University)
  • Reversible Jump Probabilistic Programming
    David A Roberts (University of Queensland)*; Marcus Gallagher (The University of Queensland); Thomas Taimre (University of Queensland)
  • Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability
    Akifumi Okuno (Kyoto University and RIKEN AIP)*; Geewook Kim (Kyoto University / RIKEN AIP); Hidetoshi Shimodaira (Kyoto University)
  • Mixed Graphical Model with Ordinal Data: Parameter Estimation and Statistical Inference
    Huijie Feng (Cornell University)*; Yang Ning (Cornell University)
  • Robust Graph Embedding with Noisy Link Weights
    Akifumi Okuno (Kyoto University and RIKEN AIP)*; Hidetoshi Shimodaira (Kyoto University)
  • Exploring Fast and Communication-Efficient Algorithms in Large-scale Distributed Networks
    Yue Yu (Tsinghua University)*; Jiaxiang Wu (Tencent AI Lab); Junzhou Huang (University of Texas at Arlington)
  • Defending against Whitebox Adversarial Attacks via Randomized Discretization
    Yuchen Zhang (Microsoft)*; Percy Liang ()
  • Fisher Information and Natural Gradient Learning in Random Deep Networks
    Shun-ichi Amari (RIKEN BSI)*
  • Robust descent using smoothed multiplicative noise
    Matthew J Holland (Osaka University)*
  • Classification using margin pursuit
    Matthew J Holland (Osaka University)*
  • Linear Queries Estimation with Local Differential Privacy
    Raef Bassily (The Ohio State University)*
  • Bayesian Learning of Neural Network Architectures
    Georgi Dikov (Technical University of Munich)*; Justin Bayer (Volkswagen Group)
  • Nonlinear Acceleration of Primal-Dual Algorithms
    Raghu Bollapragada (Northwestern); Damien Scieur (Princeton University); Alexandre d'Aspremont (Ecole Normale Superieure)*
  • Gaussian Process Latent Variable Alignment Learning
    Ieva Kazlauskaite (University of Bath)*; Carl Henrik Ek (Bristol University); Neill Campbell (University of Bath)
  • A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure
    Juho Lee (University of Oxford)*; Lancelot James (Hong Kong University of Science and Technology); Seungjin Choi (POSTECH); Francois Caron (Oxford)
  • Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior
    Gaël Letarte (Université Laval)*; Emilie Morvant (University Jean Monnet, St-Etienne); Pascal Germain (Inria)
  • Forward Amortized Inference for Likelihood-Free Variational Marginalization
    Luca Ambrogioni (Donders Institute)*; Julia Berezutskaya (University of Utrecht); Eva van den Borne (Radboud University); Umut Güçlü (Radboud University, Donders Institute for Brain, Cognition and Behaviour); Yağmur Güçlütürk ( Radboud University, Donders Institute for Brain, Cognition and Behaviour); Max Hinne (University of Amsterdam); Eric Maris (Donders Institute); Marcel van Gerven (Radboud University, Donders Institute for Brain, Cognition and Behaviour)
  • SpikeCaKe: Semi-Analytic Nonparametric Bayesian Inference forSpike-Spike Neuronal Connectivity
    Luca Ambrogioni (Donders Institute)*; Patrick Ebel (Radboud University); Max Hinne (University of Amsterdam); Umut Güçlü (Radboud University, Donders Institute for Brain, Cognition and Behaviour); Marcel van Gerven (Radboud University, Donders Institute for Brain, Cognition and Behaviour); Eric Maris (Donders Institute)
  • Scalable Gaussian Process Inference with Finite-data Mean and Variance Guarantees
    Jonathan H Huggins (Harvard)*; Trevor Campbell (UBC); Mikolaj Kasprzak (Oxford); Tamara Broderick (MIT)
  • Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization
    Jonas Kohler (ETHZ)*; Hadi Daneshmand (ETH); Aurelien Lucchi (ETH Zurich); Klaus Neymeyr (University of Rostock); Ming Zhou (University of Rostock)
  • A new evaluation framework for topic modeling algorithms based on synthetic corpora
    Hanyu Shi (Northwestern university); Martin Gerlach (Northwestern University); Isabel Diersen (Northwestern University); Doug Downey (Northwestern University); Luis Amaral (Northwestern University)*
  • On Kernel Derivative Approximation with Random Fourier Features
    Zoltan Szabo (Ecole Polytechnique)*; Bharath Sriperumbudur (Penn State)
  • Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows
    George Papamakarios (University of Edinburgh)*; David Sterratt (University of Edinburgh); Iain Murray (University of Edinburgh)
  • Optimal Transport for Multi-source Domain Adaptation under Target Shift
    Ievgen Redko (Laboratoire Hubert Curien)*; Rémi Flamary (Université Côte d’Azur); Nicolas Courty (UBS); Devis Tuia (Wageningen University and Research)
  • Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning
    Aapo Hyvarinen (UCL & U Helsinki)*; Hiroaki Sasaki (Nara Institute of Science and Technology); Richard Turner ()
  • Deep Neural Networks Learn Non-Smooth Functions Effectively
    Masaaki Imaizumi (Institute of Statistical Mathematics)*; Kenji Fukumizu (The Institute of Statistical Mathematics)
  • Attenuating Bias in Word vectors
    Sunipa Dev (University of Utah)*; Jeff Phillips (University of Utah)
  • Fisher-Rao Metric, Geometry, and Complexity of Neural Networks
    Tengyuan Liang (University of Chicago); Tomaso Poggio (MIT); Alexander Rakhlin (MIT); James Stokes ()*
  • Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives
    Hadrien Hendrikx (INRIA - Ecole Normale Supérieure)*; Laurent Massoulie (Microsoft-Inria Joint Center); Francis Bach (INRIA - Ecole Normale Supérieure)
  • Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks
    Tengyuan Liang (University of Chicago)*; James Stokes ()
  • On Constrained Nonconvex Stochastic Optimization: A Case Study for Generalized Eigenvalue Decomposition
    Zhehui Chen (Georgia Tech); Xingguo Li (University of Minnesota); Lin Yang (Princeton University); Jarvis Haupt (UMN); Tuo Zhao (Georgia Tech)*
  • Generalized Boltzmann Machine with Deep Neural Structure
    Yingru Liu (Stony Brook University); Dongliang Xie (Beijing University of Posts and Telecommunications)*; xin wang (Department of Electrical and Computer Engineering, Stony Brook University)
  • Extreme Stochastic Variational Inference: Distributed Inference for Large Scale Mixture Models
    Parameswaran Raman (UC Santa Cruz)*; Jiong Zhang (UT-Austin); Shihao Ji (Georgia State University); Hsiang-Fu Yu (Amazon); S.V.N. Vishwanathan (UCSD / Amazon); Inderjit Dhillon (University of Texas at Austin)
  • Correcting the bias in least squares regression with volume-rescaled sampling
    Michal Derezinski (UC Berkeley)*; Manfred K. Warmuth (UCSC); Daniel Hsu (Columbia University)
  • Conservative Exploration using Interleaving
    Sumeet Katariya (Univ of Wisconsin-Madison)*; Branislav Kveton (Google Research); Zheng Wen (Adobe Research); Vamsi K Potluru (Comcast Cable)
  • Conditionally Independent Multiresolution Gaussian Processes
    Jalil Taghia (Uppsala University)*; Thomas Schön (Uppsala University)
  • Active Exploration in Markov Decision Processes
    Jean Tarbouriech (FAIR); Alessandro Lazaric (FAIR)*
  • On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes
    Xiaoyu Li (Boston University); Francesco Orabona (Boston University)*
  • Bandit Online Learning with Unknown Delays
    Bingcong Li (University of Minnesota)*; Tianyi Chen (University of Minnesota); Georgios B. Giannakis (University of Minnesota)
  • Learning Invariant Representations by Kernel Warping
    Yingyi Ma (UIC); Vignesh Ganapathiraman (UIC); Xinhua Zhang (UI Chicago)*
  • β³-IRT: A New Item Response Model and its Applications
    YU CHEN (UNIVERSITY OF BRISTOL)*; Telmo M Silva Filho (Universidade Federal de Pernambuco); Ricardo B Prudencio (UFPE); Tom Diethe (Amazon); Peter Flach (University of Bristol)
  • Auditing Model Prediction Reliability After-the-Fact with Resampling Uncertainty Estimation
    Peter Schulam (Johns Hopkins University)*; Suchi Saria (Johns Hopkins University)
  • Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach
    Ryo Karakida (National Institute of Advanced Industrial Science and Technology)*; Shotaro Akaho (AIST); Shun-ichi Amari (RIKEN BSI)
  • Conditional Sparse L_p-norm Regression With Optimal Probability
    Brendan Juba (WASHINGTON UNIVERSITY ST LOUIS); David Woodruff (Carnegie Mellon University); Hai S Le (WASHINGTON UNIVERSITY ST LOUIS)*; John Hainline (Washington University in St. Louis)
  • On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition
    Marco Mondelli (Stanford University)*; Andrea Montanari (Stanford University)
  • Autoencoding any Data through Kernel Autoencoders
    Pierre Laforgue (Telecom ParisTech)*; Stéphan Clémençon (Télécom ParisTech); Florence d’Alche-Buc (Télécom ParisTech)
  • Towards Understanding the Generalization Bias of Two Layer Convolutional Linear Classifiers with Gradient Descent
    Yifan Wu (Carnegie Mellon University)*; Barnabas Poczos ( Carnegie Mellon University); Aarti Singh (Carnegie Mellon University)
  • Learning to Optimize under Non-Stationarity
    Wang Chi Cheung (IHPC, ASTAR); David Simchi-Levi (MIT); Ruihao Zhu (MIT)*
  • SPONGE: A generalized eigenproblem for clustering signed networks
    Mihai Cucuringu (University of Oxford and the Alan Turing Institute)*; Peter Davies (University of Warwick); Aldo Glielmo (Department of Physics, King's College London, Strand, London WC2R 2LS, United Kingdom); Hemant Tyagi (Alan Turing Institute)
  • Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex
    Hongyang Zhang (Carnegie Mellon University)*; Junru Shao (Carnegie Mellon University); Ruslan Salakhutdinov (Carnegie Mellon University)
  • Are we there yet? Manifold identification of gradient-related proximal methods
    Yifan Sun (University of British Columbia)*; Halyun Jeong (UBC); Julie Nutini (University of British Columbia); Mark Schmidt (University of British Columbia)
  • Hadamard Response: Estimating Distributions Privately, Efficiently, and with Little Communication
    Jayadev Acharya (Cornell University)*; Ziteng Sun (Cornell University); Huanyu Zhang (Cornell University)
  • Accelerated Bayesian Additive Regression Trees
    Jingyu He (University of Chicago)*; Saar Yalov (Arizona State University ); P. Richard Hahn (Arizona State University)
  • A Swiss Army Infinitesimal Jackknife
    Ryan Giordano (UC Berkeley)*; William T Stephenson (MIT); Runjing Liu (UC Berkeley); Michael Jordan (UC Berkeley); Tamara Broderick (MIT)
  • Online Multiclass Boosting with Bandit Feedback
    Daniel T. Zhang (University of Michigan); Young Hun Jung (University of Michigan)*; Ambuj Tewari (University of Michigan)
  • Auto-Encoding Total Correlation Explanation
    Shuyang Gao (ISI USC)*; Rob Brekelmans (USC / ISI); Greg Ver Steeg (University of Southern California); Aram Galstyan (USC Information Sciences Institute)
  • Towards Efficient Data Valuation Based on the Shapley Value
    Ruoxi Jia (UC Berkeley)*; David Dao (ETH); Boxin Wang (Zhejiang University); Frances Ann Hubis (ETH Zurich); Nick Hynes (UC Berkeley); Bo Li (University of Illinois at Urbana–Champaign); Ce Zhang (ETH); Dawn Song (UC Berkeley); Costas J. Spanos (University of California at Berkeley)
  • Bayesian optimisation under uncertain inputs
    Rafael Oliveira (The University of Sydney)*; Lionel Ott (The University of Sydney); Fabio Ramos (U Sydney)
  • Optimal Minimization of the Sum of Three Convex Functions with a Linear Operator
    Seyoon Ko (Seoul National University); Donghyeon Yu (Inha University); Joong-Ho Won (Seoul National University)*
  • Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron
    Sharan Vaswani (University of British Columbia)*; Francis Bach (INRIA - Ecole Normale Supérieure); Mark Schmidt (University of British Columbia)
  • No-regret algorithms for online $k$-submodular maximization
    Tasuku Soma (University of Tokyo)*
  • Lagrange Coded Computing: Optimal Design for Resiliency, Security, and Privacy
    Qian Yu (University of Southern California)*; Netanel Raviv (Caltech); Songze Li (University of Southern California); Seyed Mohammadreza Mousavi Kalan (University of Southern California); Mahdi Soltanolkotabi (USC); Salman Avestimehr (University of Southern California)
  • Subsampled Renyi Differential Privacy and Analytical Moments Accountant
    Yu-Xiang Wang (UC Santa Barbara)*; Borja Balle (Amazon); Shiva Kasiviswanathan (Amazon AWS AI)
  • Model Consistency for Learning with Mirror-Stratifiable Regularizers
    Jalal Fadili (GREYC, CNRS, ENSICAEN, Université de Caen); Guillaume Garrigos (École Normale Supérieure de Paris)*; Jérôme Malick (CNRS and LJK); Gabriel Peyré (CNRS and ENS)
  • From Cost-Sensitive to Tight F-measure Bounds
    Kevin Bascol (Université Saint-Etienne)*; Emonet Rémi (Laboratoire Hubert Curien); Elisa Fromont (IRISA, INRIA, FR); Amaury Habrard (Université Saint-Etienne); Guillaume METZLER (Université Saint Etienne); Marc Sebban (Université Saint-Etienne)
  • Best subset selection for multinomial logit model via a mixed-integer optimization
    Shunsuke Kamiya (Tokyo University of Agriculture and Technology)*; Ryuhei Miyashiro (Tokyo University of Agriculture and Technology); Yuichi Takano (University of Tsukuba)
  • Low-precision Random Fourier Features for Memory-constrained Kernel Approximation
    Jian Zhang (Stanford)*; Avner May (Stanford University); Tri Dao (Stanford University); Christopher Re (Stanford University)
  • Restarting Frank-Wolfe
    Thomas Kerdreux (INRIA/ ENS)*; Alexandre d'Aspremont (Ecole Normale Superieure); Sebastian Pokutta (Gatech)
  • Fast and Accurate Inference with Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level
    Hiroshi Inoue (IBM Research - Tokyo)*
  • Infinite Task Learning in RKHSs
    Romain R Brault (Telecom ParisTech); Alex Lambert (Télécom ParisTech)*; Zoltan Szabo (Ecole Polytechnique); Florence d’Alche-Buc (Télécom ParisTech); Maxime Sangnier (Sorbonne University)
  • Detection of Planted Solutions for Flat Satisfiability Problems
    Quentin Berthet (University of Cambridge)*; Jordan Ellenberg (University of Wisconsin-Madison)
  • Markov Properties of Discrete Determinantal Point Processes
    Kayvan Sadeghi (University College London)*; Alessandro Rinaldo (Carnegie Mellon University)
  • Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms
    Alihan Huyuk (Bilkent University)*; Cem Tekin (Bilkent University)
  • Distilling Policy Distillation
    Wojciech M Czarnecki (DeepMind)*; Razvan Pascanu (Google Deepmind); Simon Osindero (DeepMind); Siddhant Jayakumar (DeepMind); Grzegorz M Swirszcz (DeepMind); Max Jaderberg (Google)
  • Support Localization and the Fisher Metric for off-the-grid Sparse Regularization
    Clarice Poon (DAMTP, University of Cambridge); Nicolas Keriven (Ecole Normale Supérieure)*; Gabriel Peyré (CNRS and ENS)
  • Fast Gaussian process based gradient matching for parameter identification in systems of nonlinear ODEs
    Philippe Wenk (ETH Zurich)*; Alkis Gotovos (ETH); Stefan Bauer (MPI IS); Nico S Gorbach (); Andreas Krause (ETH Zürich); Joachim Buhmann (ETH Zurich)
  • Semi-Generative Modelling: Covariate-Shift Adaptation with Cause and Effect Features
    Julius von Kügelgen (University of Cambridge)*; Marco Loog (TU Delft); Alexander Mey (TU Delft)
  • A Continuous-Time View of Early Stopping for Least Squares Regression
    Alnur Ali ()*; Ryan Tibshirani (Carnegie Mellon University); Zico Kolter (Carnegie Mellon University)
  • Towards Clustering High-dimensional Gaussian Mixture Clouds in Linear Running Time
    Dan Kushnir (Nokia Bell Labs)*; Shirin Jalali (Bell Labs); Iraj Saniee (Nokia Bell Labs)
  • Classifying Signals on Irregular Domains via Convolutional Cluster Pooling
    Angelo Porrello (University of Modena and Reggio Emilia)*; Davide Abati (University of Modena and Reggio Emilia); SIMONE CALDERARA (University of Modena and Reggio Emilia, Italy); Rita Cucchiara (Universita Di Modena E Reggio Emilia)
  • Learning Rules-First Classifiers
    Deborah Cohen (Google)*; Amit Daniely (Google); Amir Globerson (Google); Gal Elidan (Google)
  • Wasserstein regularization for sparse multi-task regression
    Hicham Janati (INRIA)*; Marco Cuturi (ENSAE/CREST); Alexandre Gramfort (Inria)
  • Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors
    Atsushi Nitanda (The University of Tokyo / RIKEN)*; Taiji Suzuki (University of Tokyo / RIKEN)
  • Black Box Quantiles for Kernel Learning
    Anthony P Tompkins (The University of Sydney)*; Ransalu Senanayake (University of Sydney); Philippe Morere (The University of Sydney); Fabio Ramos (U Sydney)
  • Adversarial Variational Optimization of Non-Differentiable Simulators
    Gilles Louppe (University of Liège)*; Joeri Hermans (University of Liège); Kyle Cranmer (New York University)
  • Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization
    Filip de Roos (Max Planck Institute for Intelligent Systems)*; Philipp Hennig (University of Tübingen)
  • Projection Free Online Learning over Smooth Sets
    Kfir Yehuda Levy (ETH)*; Andreas Krause (ETH Zürich)
  • Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes
    Tongfei Chen (Johns Hopkins University)*; Jiri Navratil (IBM Thomas J. Watson Research Center); Vijay Iyengar (IBM Research); Karthikeyan Shanmugam (IBM Research)
  • Learning Influence-Receptivity Network Structure with Guarantee
    Ming Yu (University of Chicago)*; Varun Gupta (University of Chicago Booth School of Business); Mladen Kolar (University of Chicago Booth School of Business)
  • Iterative Bayesian Learning for Crowdsourced Regression
    Jungseul Ok (UIUC); Sewoong Oh (UIUC); Jinwoo Shin (KAIST); Yung Yi (KAIST); Yunhun Jang (KAIST)*
  • Nonconvex Matrix Factorization from Rank-One Measurements
    Yuanxin Li (Carnegie Mellon University); Cong Ma (Princeton University); Yuxin Chen (Princeton University); Yuejie Chi (CMU)*
  • Fast and Robust Shortest Paths on Manifolds Learned from Data
    Georgios Arvanitidis (Technical University of Denmark)*; Soren Hauberg (Technical University of Denmark, Denmark); Philipp Hennig (University of Tübingen); Michael Schober (Bosch Center for Artificial Intelligence)
  • Training a Spiking Neural Network with Equilibrium Propagation
    Peter E.D. O'Connor (University of Amsterdam)*
  • Learning One-hidden-layer ReLU Networks via Gradient Descent
    Xiao Zhang (University of Virginia)*; Yaodong Yu (University of Virginia); Lingxiao Wang (University of California, Los Angeles); Quanquan Gu (University of California, Los Angeles)
  • Gain estimation of linear dynamical systems using Thompson Sampling
    Matias I Müller (KTH Royal Institute of Technology)*; Cristian R Rojas (KTH Royal Institute of Technology)
  • Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit
    Shengyu Zhu (Huawei Noah's Ark Lab)*; Biao Chen (Syracuse University); Pengfei Yang (Cubist Systematic Strategies); Zhitang Chen (Huawei Noah’s Ark Lab)
  • Calibrating Deep Convolutional Gaussian Processes
    Gia-Lac Tran (EURECOM); Edwin V Bonilla (Data61); John Cunningham (); Pietro Michiardi (EURECOM); Maurizio Filippone (EURECOM)*
  • Stochastic algorithms with descent guarantees for ICA
    Pierre Ablin (Inria)*; Alexandre Gramfort (Inria); Jean-François Cardoso (CNRS - Institut d'astrophysique de Paris); Francis Bach (INRIA - Ecole Normale Supérieure)
  • Sample Complexity of Sinkhorn Divergences
    Aude Genevay (U Paris Dauphine)*; Marco Cuturi (ENSAE/CREST); Gabriel Peyré (CNRS and ENS); Francis Bach (INRIA - Ecole Normale Supérieure); Lénaïc Chizat (INRIA)
  • Adaptive Gaussian Copula ABC
    Yanzhi Chen (University of Edinburgh)*; Michael U. Gutmann (University of Edinburgh)
  • Top Feasible Arm Identification
    Julian Katz-Samuels (University of Michigan)*; Clay Scott ()
  • Direct Acceleration of SAGA using Sampled Negative Momentum
    Kaiwen Zhou (The Chinese University of Hong Kong)*; Qinghua Ding (Tsinghua University); Fanhua Shang (Xidian University); James Cheng (CUHK); Danli Li (The Chinese University of Hong Kong); Zhiquan Luo (The Chinese University of Hong Kong)
  • Does data interpolation contradict statistical optimality?
    Mikhail Belkin (Ohio State University); Alexander Rakhlin (MIT)*; Alexandre Tsybakov (CREST, ENSAE)
  • Inverting Supervised Representations with Autoregressive Neural Density Models
    Charlie Nash (The University of Edinburgh)*; Nate Kushman (Microsoft Research); Chris Williams (Edinburgh)
  • Connecting Weighted Automata and Recurrent Neural Networks through Spectral Learning
    guillaume rabusseau (McGill)*; Tianyu Li (McGill University); Doina Precup (McGill University)
  • A Family of Exact, Distribution-Free Goodness-of-Fit Tests for High-Dimensional Discrete Distributions
    Feras Saad (Massachusetts Institute of Technology)*; Cameron Freer (MIT); Nate Ackerman (Harvard University); Vikash Mansinghka (Massachusetts Institute of Technology)
  • Differentially Private Online Submodular Minimization
    Rachel Cummings (Georgia Tech)*; Adrian Rivera Cardoso (Georgia Tech)
  • Semi-supervised clustering for de-duplication
    Shrinu Kushagra (University of Waterloo)*; Shai Ben-David (University of Waterloo); Ihab F Ilyas (U. of Waterloo)
  • Finding the Bandit in a Graph: Sequential Search-and-Stop
    Pierre Perrault (Inria Lille - Nord Europe)*; Vianney Perchet (ENS Paris-Saclay & Criteo); Michal Valko (Inria)
  • Statistical Learning under Nonstationary Mixing Processes
    Steve Hanneke (Toyota Technological Institute at Chicago)*; Liu Yang (Independent)
  • On Structure Priors for Learning Bayesian Networks
    Ralf Eggeling (University of Tübingen)*; Jussi Viinikka (); Aleksis Vuoksenmaa (University of Helsinki); Mikko Koivisto ()
  • Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFs
    Alex Bauer (TU Berlin)*; Shinichi Nakajima (Technische Universität Berlin); Nico Goernitz (TU Berlin); Klaus-Robert Müller (Technische Universität Berlin)
  • Sparse Feature Selection in Kernel Discriminant Analysis via Optimal Scoring
    Alexander F Lapanowski (Texas A&M University)*; Irina Gaynanova (Texas A&M University)
  • Learning Natural Programs from a Few Examples in Real-Time
    Nagarajan Natarajan (Microsoft Research)*; Danny Simmons (Microsoft); Naren Datha (Microsoft Research); Prateek Jain (Microsoft Research); Sumit Gulwani (Microsoft Research)
  • Truncated Back-propagation for Bilevel Optimization
    Amirreza Shaban (Georgia Institute of Technology)*; Ching-An Cheng (Georgia Institute of Technology); Nathan Hatch (Georgia Institute of Technology ); Byron Boots (Georgia Institute of Technology)
  • Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data
    Victor Veitch (Columbia University)*; Morgane Austern (Columbia University); Wenda Zhou (Columbia University); Peter Orbanz (); David Blei (Columbia University)
  • Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution
    Topi Paananen (Aalto University)*; Juho Piironen (Aalto University); Michael R Andersen (Aalto University); Aki Vehtari (Aalto University)
  • Lifted Weight Learning of Markov Logic Networks Revisited
    Ondrej Kuzelka (University of Leuven)*; Vyacheslav Kungurtsev (Czech Technical University)
  • Causal discovery in the presence of missing data
    Ruibo Tu (KTH Royal Institute of Technology)*; Cheng Zhang (Microsoft); Paul Ackermann (Karolinska Institutet); Karthika Mohan (U C Berkeley); Hedvig Kjellström (KTH Royal Institute of Technology); Kun Zhang (Carnegie Mellon University)
  • Learning Tree Structures from Noisy Data
    Konstantinos Nikolakakis (Rutgers University)*; Dionysios Kalogerias (Princeton University); Anand D Sarwate (Rutgers University)
  • Active multiple matrix completion with adaptive confidence sets
    Andrea Locatelli (Uni Magdeburg)*; Alexandra Carpentier (Otto-von-Guericke-Universität Magdeburg); Michal Valko (Inria)
  • Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
    Shikhar Vashishth (Indian Institute of Science)*; Prateek Yadav (Indian Institute of Science); Manik Bhandari (Indian Institute of Science); Partha Talukdar (Indian Institute of Science)
  • Negative Momentum for Improved Game Dynamics
    Gauthier Gidel (MILA)*; Reyhane Askari Hemmat (MILA); Mohammad Pezeshki (MILA); Gabriel Huang (MILA); Rémi Le Priol (MILA); Simon Lacoste-Julien (University of Montreal); Ioannis Mitliagkas (University of Montreal)
  • Deep learning with differential Gaussian process flows
    Pashupati R Hegde (Aalto University)*; Markus Heinonen (Aalto University); Harri Lähdesmäki (Aalto University); Samuel Kaski (Aalto University)
  • Data-dependent compression of random features for large-scale kernel approximation
    Raj Agrawal (MIT)*; Jonathan H Huggins (Harvard); Trevor Campbell (UBC); Tamara Broderick (MIT)
  • Large-Margin Classification in Hyperbolic Space
    Hyunghoon Cho (MIT)*; Benjamin DeMeo (Harvard University); Jian Peng (UIUC); Bonnie Berger (MIT)
  • Generalizing the theory of cooperative inference
    Pei Wang (Rutgers University-Newark)*; Pushpi Paranamana (Rutgers University-Newark); Patrick Shafto (Rutgers University)
  • MaxHedge: Maximizing a Maximum Online with Theoretical Performance Guarantees
    Stephen U Pasteris (University College London)*; Fabio Vitale (University of Lille); Kevin Chan (US army); Shiqiang Wang (IBM Research)
  • The Gaussian Process Autoregressive Regression Model (GPAR)
    James R Requeima (University of Cambridge)*; Wessel P Bruinsma (University of Cambridge); William Tebbutt (University of Cambridge); Richard Turner ()
  • Towards Optimal Transport with Global Invariances
    David Alvarez-Melis (MIT)*; Stefanie Jegelka (MIT); Tommi Jaakkola (MIT)
  • Unsupervised Alignment of Embeddings with Wasserstein Procrustes
    Edouard Grave (Facebook AI Research)*; Armand Joulin (Facebook AI Research); Quentin Berthet (University of Cambridge)
  • Sequential Patient Recruitment and Allocation for Adaptive Clinical Trials
    Onur Atan (UCLA)*; William Zame (UCLA); Mihaela van der Schaar ()
  • Probabilistic Forecasting with Spline Quantile Function RNNs
    Konstantinos Benidis (Amazon); Jan Gasthaus (Amazon Research)*; Bernie Wang (Amazon); Syama Sundar Rangapuram (Amazon); David Salinas (Amazon); Valentin Flunkert (Amazon); Tim Januschowski (Amazon Research)
  • Exponential Weights on the Hypercube in Polynomial Time
    Sudeep Raja Putta (University of Massachusetts Amherst)*; Abhishek Shetty (Microsoft Research)
  • Sharp Analysis of Learning with Discrete Losses
    Alex Nowak (INRIA, Ecole Normale Supérieure); Francis Bach (INRIA - Ecole Normale Supérieure); Alessandro Rudi (INRIA, Ecole Normale Superieure)*
  • Designing Optimal Binary Rating Systems
    Nikhil Garg (Stanford University)*; Ramesh Johari (Stanford University)
  • Stochastic Negative Mining for Learning with Large Output Spaces
    Sashank Reddi (Google)*; Satyen Kale (Google); Felix Yu (Google); Daniel Holtmann-Rice (Google); Jiecao Chen (Indiana University Bloomington); Sanjiv Kumar (Google)
  • Learning One-hidden-layer Neural Networks under General Input Distributions
    Weihao Gao (UIUC); Ashok V Makkuva (University of Illinois at Urba); Sewoong Oh (UIUC)*; Pramod Viswanath (UIUC)
  • A Geometric Perspective on the Transferability of Adversarial Directions
    Zachary B Charles (University of Wisconsin - Madison)*; Harrison Rosenberg (University of Wisconsin-Madison); Dimitris Papailiopoulos (University of Wisconsin-Madison)
  • Non-linear process convolutions for multi-output Gaussian processes
    Mauricio A Alvarez (University of Sheffield)*; Wil Ward (University of Sheffield)
  • Lovász Convolutional Networks
    Prateek Yadav (Indian Institute of Science)*; Madhav R Nimishakavi (Indian Institute of Science); Naganand Yadati (Indian Institute of Science); Shikhar Vashishth (Indian Institute of Science); Arun Rajkumar (Conduent Labs); Partha Talukdar (Indian Institute of Science)
  • Bridging the gap between regret minimization and best arm identification, with application to A/B tests
    Rémy Degenne (CWI); Thomas Nedelec (Criteo)*; Clement Calauzenes (Criteo); Vianney Perchet (ENS Paris-Saclay)
  • Gaussian process modulated Cox processes under linear inequality constraints
    Andrés F LOPEZ-LOPERA (Mines Saint-Etienne)*; ST John (PROWLER.io); Nicolas Durrande (PROWLER.io)
  • Implicit Kernel Learning
    Chun-Liang Li (Carnegie Mellon University)*; Wei-Cheng Chang (Carnegie Mellon University); Youssef Mroueh (IBM Research); Yiming Yang (Carnegie Mellon University); Barnabas Poczos ( Carnegie Mellon University)
  • Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature
    Pier Giuseppe PGS Sessa (ETH Zürich)*; Maryam Kamgarpour (ETH Zürich); Andreas Krause (ETH Zürich)
  • Variational Information Planning for Sequential Decision Making
    Jason Pacheco (Brown University)*; John Fisher (MIT)
  • Renyi Differentially Private ERM for Smooth Objectives
    Chen Chen (University of Georgia); Jaewoo Lee (University of Georgia)*; Dan Kifer (Pennsylva State Univ., USA)
  • Projection-Free Bandit Convex Optimization
    Lin Chen (Yale University)*; Mingrui Zhang (Yale University); Amin Karbasi (Yale)
  • Provable Robustness of ReLU networks via Maximization of Linear Regions
    Francesco Croce (Saarland University); Maksym Andriushchenko (Saarland University); Matthias Hein (University of Tuebingen)*
  • Test without Trust: Optimal Locally Private Distribution Testing
    Jayadev Acharya (Cornell University); Clement Canonne (Stanford University)*; Cody Freitag (Cornell University); Himanshu Tyagi (IISC)
  • Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets
    Mehrdad Ghadiri (University of British Columbia)*; Mark Schmidt (University of British Columbia)
  • On Euclidean k-Means Clustering with alpha-Center Proximity
    Amit Deshpande (Microsoft Research); Anand Louis (Indian Institute of Science, Bangalore, India); Apoorv V Singh (Indian Institute of Science)*
  • Noisy Blackbox Optimization using Multi-fidelity Queries: A Tree Search Approach
    Rajat Sen (University of Texas at Austin)*; Kirthevasan Kandasamy (Carnegie Mellon University); Sanjay Shakkottai (University of Texas at Austin)
  • Safe Convex Learning under Uncertain Constraints
    Ilnura Usmanova (ETH Zurich)*; Andreas Krause (ETH Zürich); Maryam Kamgarpour ()
  • The non-parametric bootstrap and spectral analysis in moderate and high-dimension
    Noureddine El Karoui (UC Berkeley)*; Elizabeth Purdom (UC Berkeley)
  • Knockoffs for the Mass: New Feature Importance Statistics with False Discovery Guarantees
    Jaime Roquero Gimenez (Stanford University); Amirata Ghorbani (Stanford University); James Zou (Stanford University)*
  • Training Variational Autoencoders with Buffered Stochastic Variational Inference
    Rui Shu (Stanford University); Hung Bui (Google)*; Jay Whang (Stanford University); Stefano Ermon (Stanford University)
  • Regularized Contextual Bandits
    Xavier Fontaine (ENS Paris-Saclay)*; Vianney Perchet (Ecole Normale Supérieure Paris-Saclay, Université Paris Saclay); Quentin Berthet (University of Cambridge)
  • Risk-Sensitive Generative Adversarial Imitation Learning
    Jonathan Lacotte (Stanford University)*; Mohammad Ghavamzadeh (FAIR); Yinlam Chow (DeepMind); Marco Pavone (Stanford University)
  • Learning Controllable Fair Representations
    Jiaming Song (Stanford)*; Pratyusha Kalluri (Stanford University); Aditya Grover (Stanford University); Shengjia Zhao (Stanford University); Stefano Ermon (Stanford University)
  • Multi-Task Time Series Analysis applied to Drug Response Modelling
    Alex Bird (Alan Turing Institute)*; Chris Williams (Edinburgh); Christopher Hawthorne (Queen Elizabeth University Hospital)
  • Improving the Stability of the Knockoff Procedure: Multiple Simultaneous Knockoffs and Entropy Maximization
    Jaime Roquero Gimenez (Stanford University); James Zou (Stanford University)*
  • Know Your Boundaries: Constraining Gaussian Processes by Variational Harmonic Features
    Arno Solin (Aalto University)*; Manon Kok (Delft University of Technology)
  • Distributional reinforcement learning with linear function approximation
    Marc G. Bellemare (Google Brain)*; Nicolas Le Roux (Google); Pablo Samuel Castro (Google); Subhodeep Moitra (Google, Inc.)
  • Matroids, Matchings, and Fairness
    Flavio Chierichetti (Sapienza University); Ravi Kumar (Google)*; Silvio Lattanzi (Google); Sergei Vassilvtiskii (Google)
  • Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function
    Wojciech Tarnowski (Jagiellonian University in Kraków)*; Piotr Warchoł (Jagiellonian University in Kraków); Stanisław Jastrzębski (Jagiellonian University); Jacek Tabor (Jagiellonian University in Kraków ); Maciej Nowak (Jagiellonian University in Kraków)
  • The Termination Critic
    Anna Harutyunyan (DeepMind)*; Will Dabney (DeepMind); Diana Borsa (DeepMind); Nicolas Heess (DeepMind); Remi Munos (DeepMind); Doina Precup (McGill University)
  • Consistent Online Optimization: Convex and Submodular
    Mohammad Reza Karimi Jaghargh (ETH Zurich)*; Andreas Krause (ETH Zürich); Silvio Lattanzi (Google); Sergei Vassilvtiskii (Google)
  • Learning Determinantal Point Processes by Sampling Inferred Negatives
    Zelda Mariet (Massachusetts Institute of Technology)*; Mike Gartrell (Criteo AI Lab); Suvrit Sra (Massachusetts Institute of Technology, USA)
  • Probabilistic Semantic Inpainting with Pixel Constrained CNNs
    Emilien Dupont (Schlumberger)*
  • Least Squares Estimation of Weakly Convex Functions
    Sun Sun (University of Waterloo); Yaoliang Yu (University of Waterloo)*
  • Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding
    Nathan Kallus (Cornell Tech)*; Xiaojie Mao (Cornell University); Angela Zhou (Cornell University)
  • Amortized Variational Inference with Graph Convolutional Networks for Gaussian Processes
    Linfeng Liu (Tufts University)*; Liping Liu (Tufts University)
  • Online Decentralized Leverage Score Sampling for Streaming Multidimensional Time Series
    Rui Xie (University of Georgia); Zengyan Wang (University of Georgia); Shuyang Bai (University of Georgia); Ping Ma (University of Georgia); Wenxuan Zhong ()*
  • Interpretable Cascade Classifiers with Abstention
    Matthieu Clertant (University Paris 6)*; Nataliya Sokolovska (University Paris 6); Yann Chevaleyre (Université Paris Dauphine); Blaise HANCZAR (Université d Evry)
  • Kernel Exponential Family Estimation via Doubly Dual Embedding
    Bo Dai (Google Brain)*; Hanjun Dai (Georgia Tech); Arthur Gretton (Gatsby Computational Neuroscience Unit); Dale E Schuurmans (Google Inc.); Le Song (Ant Financial & Georgia Institute of Technology ); Niao He (University of Illinois at Urbana-Champaign)
  • Revisiting Adversarial Risk
    Arun Sai Suggala (Carnegie Mellon University)*; Adarsh Prasad (Carnegie Mellon University); Pradeep Ravikumar (Carnegie Mellon University)
  • A Memoization Framework for Scaling Submodular Optimization to Large Scale Problems
    Rishabh Krishnan Iyer (Microsoft Corporation)*; Jeffrey Bilmes (University of Washington)
  • Bernoulli Race Particle Filters
    Sebastian M Schmon (University of Oxford)*; Arnaud Doucet (Oxford University); George Deligiannidis (Oxford)
  • Augmented Ensemble MCMC sampling in Factorial Hidden Markov Models
    Kaspar Martens (University of Oxford); Michalis Titsias (Athens University); Christopher Yau (University of Birmingham)*
  • Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models
    Anton Mallasto (University of Copenhagen)*; Soren Hauberg (Technical University of Denmark, Denmark); Aasa Feragen (University of Copenhagen, Denmark)
  • Unbiased Smoothing using Particle Independent Metropolis-Hastings
    Lawrece T Middleton (University of Oxford)*; Arnaud Doucet (Oxford University); Pierre Jacob (Harvard University); George Deligiannidis (Oxford)
  • Two-temperature logistic regression based on the Tsallis divergence
    Ehsan Amid (UCSC)*; Manfred K. Warmuth (UCSC); Sriram Srinivasan (UC Santa Cruz)
  • Avoiding Latent Variable Collapse with Generative Skip Models
    Adji Bousso Dieng (Columbia University)*; Yoon Kim (Harvard University); Alexander Rush (Harvard); David Blei (Columbia University)
  • SMOGS: Social Network Metrics of Game Success
    Fan Bu (Duke University)*; Sonia Xu (Duke University); Katherine Heller (Duke University); Alexander Volfovsky (Duke University)
  • Fast Algorithms for Sparse Reduced-Rank Regression
    Benjamin Dubois (Ecole des Ponts ParisTech)*; Guillaume Obozinski (Ecole des Ponts ParisTech); Jean-François Delmas (Ecole des Ponts ParisTech)
  • Stay Positive: The Benefits of Better Models in Stochastic Optimization
    Hilal Asi (Stanford University)*; John Duchi (Stanford University)
  • Online learning with feedback graphs and switching costs
    Anshuka Rangi (University of California San Diego)*; Massimo Franceschetti (UC San Diego )
  • Almost-Exact Matching with Replacement for Causal Inference
    Awa Dieng (Duke University, USA); Yameng Liu (Duke University, USA); Sudeepa Roy (Duke University, USA); Cynthia Rudin (Duke)*; Alexander Volfovsky (Duke University)
  • Statistical Optimal Transport via Factored Couplings
    Aden Forrow (MIT)*; Jan-Christian Hütter (MIT); Mor Nitzan (Broad Institute); Philippe Rigollet (MIT); Geoffrey Schiebinger (MIT, Broad Institute); Jonathan Weed (MIT)
  • $HS^2$: Active Learning over Hypergraphs
    I Chien (UIUC)*; Huozhi Zhou (UIUC); Pan Li (UIUC)
  • Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric and Particle-Based Approach
    Alexander Lin (Harvard University)*; Yingzhuo Zhang (Harvard University); Jeremy Heng (Harvard University); Stephen Allsop (Massachusetts Institute of Technology); Kay Tye (Salk Institute for Biological Sciences); Pierre Jacob (Harvard University); Demba Ba (Harvard)
  • Efficient Nonconvex Empirical Risk Minimization via Adaptive Sample Size Methods
    Aryan Mokhtari (MIT)*; Asuman Ozdaglar (MIT); Ali Jadbabaie ()
  • An Optimal Control Approach to Sequential Machine Teaching
    Laurent Lessard (University of Wisconsin-Madison); Xuezhou Zhang (University of Wisconsin-Madison)*; Xiaojin Zhu (University of Wisconsin-Madison)
  • Smoothed Online Optimization for Regression and Control
    Gautam Goel (California Institute of Technology)*; Adam Wierman (California Institute of Technology)
  • Variational Compressive Sensing using Uncertainty Autoencoders
    Aditya Grover (Stanford University)*; Stefano Ermon (Stanford University)
  • Structured Disentangled Representations
    Babak Esmaeili (Northeastern University)*; Hao Wu (Northeastern University); Sarthak Jain (Northeastern University); Alican Bozkurt (Northeastern University); N Siddharth (Unversity of Oxford); Brooks Paige (Alan Turing Institute); Dana Brooks (Northeastern University); Jennifer Dy (Northeastern); Jan-Willem van de Meent (Northeastern)
  • Estimating Network Structure from Incomplete Event Data
    Ben Mark (University of Wisconsin-Madison)*; Garvesh Raskutti (UW-Madison); Rebecca Willett (U Chicago)
  • Locally Private Mean Estimation: Z-test and Tight Confidence Intervals
    Marco Gaboardi (Univeristy at Buffalo); Ryan Rogers (); Or Sheffet (University of Alberta)*
  • Estimation of Non-Normalized Mixture Models
    Takeru Matsuda (U Tokyo)*; Aapo Hyvarinen (UCL & U Helsinki)
  • Rotting bandits are no harder than stochastic bandits
    Julien Seznec (lelivrescolaire.fr)*; Andrea Locatelli (Uni Magdeburg); Alexandra Carpentier (Otto-von-Guericke-Universität Magdeburg); Alessandro Lazaric (FAIR); Michal Valko (Inria)
  • A Topological Regularizer for Classifiers via Persistent Homology
    Chao Chen (Stony Brook University)*; Xiuyan Ni (City University of New York); Qinxun Bai (Boston University); Yusu Wang (Ohio State University)
  • Overcomplete Independent Component Analysis via SDP
    Anastasia Podosinnikova (MIT)*; Amelia Perry (MIT); Alex Wein (MIT); Alex Wein (NYU); Francis Bach (INRIA - Ecole Normale Supérieure); Alexandre d'Aspremont (Ecole Normale Superieure); David Sontag (MIT)
  • Doubly Semi-Implicit Variational Inference
    Dmitry Molchanov (National Research University Higher School of Economics, Samsung)*; Valery Kharitonov (National Research University Higher School of Economics); Artem Sobolev (Samsung); Dmitry P Vetrov (Higher School of Economics)
  • LocalNysation: A bottom up approach to efficient localized kernel regression
    Nicole Muecke (University of Stuttgart)*
  • Scalable High-Order Gaussian Process Regression
    Shandian Zhe (University of Utah)*; Wei Xing (University of Utah); Robert Kirby (University of Utah)
  • A Higher-Order Kolmogorov-Smirnov Test
    Veeranjaneyulu Sadhanala (Carnegie Mellon University)*; Aaditya Ramdas (Carnegie Mellon University); Yu-Xiang Wang (UC Santa Barbara); Ryan Tibshirani (CMU)
  • Bayesian Learning of Conditional Kernel Mean Embeddings for Automatic Likelihood-Free Inference
    Kelvin Hsu (University of Sydney)*; Fabio Ramos (U Sydney)
  • Parallel Asynchronous Stochastic Coordinate Descent with Auxiliary Variables
    Hsiang-Fu Yu (Amazon)*; Cho-Jui Hsieh (UCLA, Google Research); Inderjit Dhillon (University of Texas at Austin)
  • Credit Assignment Techniques in Stochastic Computation Graphs
    Theophane Weber (DeepMind)*; Nicolas Heess (DeepMind); Lars Buesing (DeepMind); David Silver (-)
  • Efficient Bayesian Optimization for Target Vector Estimation
    Anders Kirk Uhrenholt (University of Glasgow)*; Bjoern Sand Jensen (University of Glasgow)
  • Correspondence Analysis Using Neural Networks
    Hsiang Hsu (Harvard University)*; Salman Salamatian (MIT); Flavio Calmon (Harvard University)
  • Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
    Jean Feydy (École Normale Supérieure)*; Thibault Séjourné (ENS); Alain TROUVE (Ecole Normale Superieure de Cachan); François-Xavier Vialard (Université de Marne-la-Vallée); Gabriel Peyré (CNRS and ENS)
  • Multi-Observation Regression
    Rafael Frongillo (CU Boulder); Nishant Mehta (University of Victoria)*; Tom Morgan (Harvard University); Bo Waggoner (University of Colorado)
  • Adaptive MCMC via Combining Local Samplers
    Kiarash Shaloudegi (Imperial College London); Andras Gyorgy (DeepMind)*
  • Variance reduction properties of the reparameterization trick
    Ming Xu (University of New South Wales); Matias Quiroz (University of New South Wales)*; Robert Kohn (University of New South Wales); Scott SIsson ()
  • Hierarchical Clustering for Euclidean Data
    Vaggos Chatziafratis (Stanford University, California)*; Moses Charikar (Stanford University, California); Rad Niazadeh (Stanford University, California); Grigory Yaroslavtsev (Indiana University, Bloomington)
  • Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization
    Zhe Wang (Ohio State University)*; Yi Zhou (Ohio State University); Yingbin Liang (The Ohio State University); Guanghui Lan (Georgia Tech)
  • Variational Noise-Contrastive Estimation
    Benjamin J Rhodes (University of Edinburgh)*; Michael U. Gutmann (University of Edinburgh)
  • Improving Quadrature for Constrained Integrands
    Henry R Chai (Washington University in St. Louis)*; Roman Garnett (-)
  • High Dimensional Inference in Partially Linear Models
    Ying Zhu (Purdue University )*; Zhuqing Yu (AbbVie Inc); Guang Cheng (Purdue University)
  • Cost aware Inference for IoT Devices
    Pengkai Zhu (Boston University)*; Nan Feng (); Durmus Alp Emre Acar (Boston University); Prateek Jain (Microsoft Research); Venkatesh Saligrama (Boston University)
  • Banded Matrix Operators for Gaussian Markov Models in the Automatic Differentiation Era
    Nicolas Durrande (PROWLER.io)*; Vincent Adam (PROWLER.io); Lucas Bordeaux (PROWLER.io); Stefanos Eleftheriadis (Prowler.io); James Hensman (PROWLER.io)
  • A Unified Weight Learning Paradigm for Multi-view Learning
    Lai Tian (Northwestern Polytechnical University)*; Feiping Nie (Northwestern Polytechnical University); Xuelong Li (Northwestern Polytechnical University, China; Chinese Academy of Science, China)
  • Region-Based Active Learning
    Corinna Cortes (Google); Giulia DeSalvo (Google); Claudio Gentile (Google Research); Mehryar Mohri (NYU); Ningshan Zhang (NYU)*
  • Precision Matrix Estimation with Noisy and Missing Data
    Roger Fan (University of Michigan)*; Byoungwook Jang (University of Michigan); Yuekai Sun (University of Michigan); Shuheng Zhou (University of California, Riverside)
  • Exploring $k$ out of Top $\rho$ Fraction of Arms in Stochastic Bandits
    Wenbo Ren (Ohio State University)*; Jia Liu (Iowa State University); Ness Shroff (The Ohio State University)
  • AutoML from Service Provider's Perspective: Multi-device, Multi-tenant Model Selection with GP-EI
    Chen Yu (University of Rochester)*; Bojan Karlaš (); Jie Zhong (Cal State LA); Ce Zhang (ETH); Ji Liu (University of Rochester)
  • On Theory for BART
    Veronika Rockova (University of Chicago)*; Enakshi Saha (University of Chicago)
  • Deep Conditioned Poisson Factor Model for Multi-label Learning
    Rajat Panda (IIT Kanpur); Ankit Pensia (Indian Institute of Technology Kanpur); Mingyuan Zhou (University of Texas at Austin); Piyush Rai (IIT Kanpur)*
  • On the Dynamics of Gradient Descent for Autoencoders
    Thanh V Nguyen (Iowa State University)*; Chinmay Hegde (Iowa State University); Raymond K. W. Wong (Texas A&M University)
  • Complexities in Projection-Free Stochastic Non-convex Minimization
    Zebang Shen (Zhejiang University; Tencent AI Lab)*; Hui Qian (Zhejiang University); Cong Fang (Peking University); Peilin Zhao (Tencent AI Lab); Junzhou Huang (University of Texas at Arlington)
  • Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
    Mike H Wu (Stanford University)*; Stefano Ermon (Stanford University); Noah Goodman (Stanford University)
  • Efficient Greedy Coordinate Descent for Composite Problems
    Sai Praneeth Karimireddy (EPFL)*; Anastasia Koloskova (EPFL); Sebastian Stich (EPFL); Martin Jaggi (EPFL)
  • Decentralized Continuous Submodular Maximization
    Jiahao Xie (Zhejiang University)*; Chao Zhang (Zhejiang University); Zebang Shen (Zhejiang University; Tencent AI Lab); Chao Mi (Zhejiang University); Hui Qian (Zhejiang University)
  • Adaptive Rao-Blackwellisation in Gibbs Sampling for Probabilistic Graphical Models
    Craig Kelly (University of Memphis)*; Somdeb Sarkhel (Adobe); Deepak Venugopal (University of Memphis)
  • Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
    Dhruv Malik (UC Berkeley); Ashwin Pananjady (UC Berkeley)*; Kush Bhatia (UC Berkeley); Koulik Khamaru (University of California Berkeley); Peter Bartlett (University of California, Berkeley); Martin Wainwright (University of California at Berkeley)
  • Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective
    Anirudh Vemula (Carnegie Mellon University)*; Wen Sun (Carnegie Mellon University); J. Andrew Bagnell (Carnegie Mellon University, USA)
  • Sampling from Non-Log-Concave Distributions via Variance-Reduced Gradient Langevin Dynamics
    Difan Zou (University of California, Los Angeles ); Pan Xu (UCLA); Quanquan Gu (University of California, Los Angeles)*
  • Graph to Graph: a Topology Aware Approach for Graph Structures Learning and Generation
    Mingming Sun (Baidu Research)*; Ping Li (Baidu Research)
  • Imitation-Regularized Offline Learning
    Yifei Ma (Amazon)*; Yu-Xiang Wang (UC Santa Barbara); Balakrishnan Narayanaswamy (Amazon)
  • A maximum-mean-discrepancy goodness-of-fit test for censored data
    Tamara Fernandez (UCL)*; Arthur Gretton (Gatsby Computational Neuroscience Unit)
  • Sobolev Descent
    Youssef Mroueh (IBM Research)*; Tom Sercu (IBM); Anant Raj (Max-Planck Institute for Intelligent Systems)
  • Learning the structure of a nonstationary vector autoregression
    Daniel Malinsky (Johns Hopkins University)*; Peter Spirtes (Carnegie Mellon University)
  • Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning
    Tadashi Kozuno (Okinawa Institute of Science and Technology)*; Eiji Uchibe (ATR Computational Neuroscience Labs.); Kenji Doya (Okinawa Institute of Science and Technology)
  • A Fast Sampling Algorithm for Maximum Inner Product Search
    QIN DING (University of California, Davis)*; Cho-Jui Hsieh (UC Davis); Hsiang-Fu Yu ()
  • Minimum Volume Topic Modeling
    Byoungwook Jang (University of Michigan)*; Alfred Hero (University of Michigan)
  • Binary Space Partitioning Forests
    Xuhui Fan (UNSW)*; Bin Li (Fudan University); Scott SIsson ()
  • Improved Graph based Semi-Supervised Learning
    Krishnamurthy Viswanathan (Google)*; Sushant Sachdeva (University of Toronto); Andrew Tomkins (Google); Sujith Ravi ()
  • Optimizing over a Restricted Policy Class in MDPs
    Ershad Banijamali (UNIVERSITY OF WATERLOO)*; Yasin Abbasi-Yadkori (Adobe Research); Mohammad Ghavamzadeh (FAIR); Nikos Vlassis (Netflix)
  • Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate
    Mor Shpigel Nacson (Technion)*; Nathan Srebro (Toyota Technical Institute of Chicago); Daniel Soudry (Technion)
  • Multilayer Switch Networks for Generating Discrete Data
    Payam Delgosha (UC Berkeley)*; Naveen Goela (Tanium Data Science)
  • A recurrent Markov state-space generative model for sequences
    Anand Ramachandran (University of Illinois at Urbana-Champaign)*; Steve Lumetta (University of Illinois at Urbana-Champaign ); Eric Klee (Mayo Clinic); Deming Chen (University of Illinois at Urbana-Champaign)
  • A Potential Outcomes Calculus for Identifying Conditional Path-Specific Effects
    Daniel Malinsky (Johns Hopkins University)*; Ilya Shpitser (Johns Hopkins University); Thomas Richardson (University of Washington)
  • Adversarial Discrete Sequence Generation without Explicit NeuralNetworks as Discriminators
    Zhongliang Li (Google)*; Tian Xia (Pingan Technology); Kaihe Xu (Pingan Technology); Xingyu Lou (Pingan Technology); Shaojun Wang (); Jing Xiao (Ping An Technology (Shenzhen) Co., Ltd)
  • Adaptive Estimation for Approximate k-Nearest-Neighbor Computations
    Daniel LeJeune (Rice University)*; Reinhard Heckel (Rice University); richard baraniuk (Rice University)
  • Model-Free Control via Reduction to Expert Prediction
    Yasin Abbasi-Yadkori (Adobe Research)*; Nevena Lazic (Google); Csaba Szepesvari (DeepMind/University of Alberta)
  • Learning Predictive Models That Transport
    Adarsh Subbaswamy (Johns Hopkins University)*; Peter Schulam (Johns Hopkins University); Suchi Saria (Johns Hopkins University)
  • Structured Robust Submodular Maximization: Offline and Online Algorithms
    Alfredo Torrico (Georgia Tech)*; Nika Haghtalab (Microsoft); Nima Anari (Stanford); Seffi Naor (Technion); Sebastian Pokutta (Gatech); Mohit Singh (Georgia Tech)
  • Sample-Efficient Imitation Learning via Generative Adversarial Nets
    Lionel Blondé (Hesso/UniGe)*
  • Probabilistic Multilevel Clustering via Composite Transportation Distance
    Nhat Ho (University of California, Berkeley)*; Viet Huynh (Monash University); Dinh Phung (Monash University); Michael Jordan (UC Berkeley)
  • A General Framework for Multi-fidelity Bayesian Optimization with Gaussian Processes
    Jialin Song (Caltech)*; Yuxin Chen (Caltech); Yisong Yue (Caltech)
  • Online Algorithm for Unsupervised Sensor Selection
    Arun Verma (IIT Bombay); Manjesh Kumar Hanawal (IIT Bombay); Csaba Szepesvari (DeepMind/University of Alberta)*; Venkatesh Saligrama (Boston University)
  • Best of many worlds: Robust model selection for online supervised learning
    Vidya Muthukumar (UC Berkeley)*; Mitas Ray (UC Berkeley); Anant Sahai (UC Berkeley); Peter Bartlett (University of California, Berkeley)
  • Accelerating Imitation Learning with Predictive Models
    Ching-An Cheng (Georgia Institute of Technology)*; Xinyan Yan (Georgia Institute of Technology); Evangelos Theodorou (Georgia Institute of Technology); Byron Boots (Georgia Institute of Technology)
  • Online Learning in Kernelized Markov Decision Processes
    Sayak Ray Chowdhury (Indian Institute of Science)*; Aditya Gopalan (Indian Institute of Science (IISc), Bangalore)
  • Lifting high-dimensional non-linear models with Gaussian regressors
    Christos Thrampoulidis (University of California, Santa Barbara)*; Ankit Singh Rawat (Google)
  • Domain-size Aware Markov Logic Networks
    Happy Mittal (IIT delhi)*; Ayush Bhardwaj (IIT delhi); Vibhav G Gogate (The University of Texas at Dallas); Parag Singla (IIT Delhi)
  • Database Alignment with Gaussian Features
    Osman E Dai (Georgia Institute of Technology)*; Daniel Cullina (Princeton University); Negar Kiyavash (University of Illinois at Urbana-Champaign)
  • Size of Interventional Markov Equivalence Classes in random DAG models
    Dmitriy Katz (IBM Research); Karthikeyan Shanmugam (IBM Research)*; Chandler Squires (Massachusetts Institute of Technology); Caroline Uhler (MIT)
  • Reparameterizing Distributions on Lie Groups
    Tim R Davidson (University of Amsterdam)*; Pim de Haan (University of Amsterdam); Luca Falorsi (University of Amsterdam); Patrick Forré (University of Amsterdam)
  • Revisit Batch Normalization: New Understanding and Refinement via Composition Optimization
    Xiangru Lian (University of Rochester)*; Ji Liu (University of Rochester)
  • Multi-Order Information for Working Set Selection of Sequential Minimal Optimization
    Qimao Yang (East China Normal University); Changrong Li (CFETS Information Technology); Jun Guo (East China Normal University)*
  • Harmonizable mixture kernels with variational Fourier features
    Zheyang Shen (Aalto University)*; Markus Heinonen (Aalto University); Samuel Kaski (Aalto University)
  • Multiscale Gaussian Process Level Set Estimation
    Shubhanshu Shekhar (University of California, San Diego)*; Tara Javidi (University of California San Diego)
  • Bayesian Nonparametric Coalescent-Tree Priors for VAEs
    Sharad Vikram (UCSD)*; Matthew D Hoffman (Google); Matthew J Johnson (Google Brain)
  • Adversarial Learning of a Sampler Based on an Unnormalized Distribution
    Chunyuan Li (Microsoft Research)*; Ke Bai (Duke University); Jianqiao Li (Duke University); Guoyin Wang (Duke University); Changyou Chen (University at Buffalo); Lawrence Carin Duke (CS)
  • Active Ranking with Subset-wise Preferences in the Plackett-Luce model
    Aadirupa Saha (Indian Institute of Science)*; Aditya Gopalan (Indian Institute of Science (IISc), Bangalore)
  • Recovery Guarantees For Quadratic Tensors With Sparse Observations
    Hongyang Zhang (Stanford University)*; Vatsal Sharan (Stanford University); Moses Charikar (Stanford University, California); Yingyu Liang (University of Wisconsin Madison)
  • Sample Efficient Graph-Based Optimization with Noisy Observations
    Thanh Tan Nguyen (Queensland University of Technology)*; Ali Shameli (Stanford University); Yasin Abbasi-Yadkori (Adobe Research); Anup Rao (Adobe Research); Branislav Kveton (Google Research)
  • Robustness Guarantees for Density Clustering
    Heinrich Jiang (Google)*; Jennifer Jang (Uber); Ofir Nachum (Google)
  • Fixing Mini-batch Sequences with Hierarchical Robust Partitioning
    Shengjie Wang (University of Washington, Seattle)*; Wenruo Bai (University of Washington, Seattle); Chandrashekhar Lavania (University Of Washington); Jeff Bilmes (UW)
  • Multitask Metric Learning: Theory and Algorithm
    Boyu Wang (Princeton University)*; Hejia Zhang (Princeton); Peng Liu (University of Toronto); Zebang Shen (Zhejiang University; Tencent AI Lab); Joelle Pineau (McGill / Facebook)
  • Efficient Bayes Risk Estimation for Cost-Sensitive Classification
    Daniel Andrade (NEC)*; Yuzuru Okajima (NEC)
  • Interpreting Black Box Predictions using Fisher Kernels
    Rajiv Khanna (University of California at Berkeley)*; Been Kim (Google); Joydeep Ghosh (UT Austin); Sanmi Koyejo (University of Illinois, Urbana-Champaign)
  • Representation Learning on Graphs: A Reinforcement Learning Application
    Sephora Madjiheurem (University College London)*; Laura Toni (UCL)
  • ABC-Strategy: Budgeted Experimental Design for Targeted Causal Structure Discovery
    Raj Agrawal (MIT)*; Caroline Uhler (MIT); Chandler Squires (Massachusetts Institute of Technology); Karren D Yang (MIT); Karthikeyan Shanmugam (IBM Research)
  • Batched Stochastic Bayesian Optimization via Combinatorial Constraints Design
    Kevin K Yang (Caltech)*; Yuxin Chen (Caltech); Yisong Yue (Caltech)
  • Convergence of Gradient Descent on Separable Data
    Mor Shpigel Nacson (Technion)*; Jason Lee (USC); Suriya Gunasekar (TTI Chicago); Pedro Henrique Pamplona Savarese (Toyota Technical Institute of Chicago); Nathan Srebro (Toyota Technical Institute of Chicago); Daniel Soudry (Technion)
  • Structured Representations for Reviews: Aspect-Based Variational Hidden Factor Models
    Babak Esmaeili (Northeastern University)*; Byron Wallace (Northeastern); Jan-Willem van de Meent (Northeastern)
  • Adaptive Minimax Regret against Smooth Logarithmic Losses over High-Dimensional l1-Balls via Envelope Complexity
    Kohei Miyaguchi (The University of Tokyo)*; Kenji Yamanishi (The University of Tokyo)
  • Low-Dimensional Density Ratio Estimation for Covariate Shift Correction
    Petar Stojanov (Carnegie Mellon University)*; Kun Zhang (Carnegie Mellon University); Mingming Gong (University of Pittsburgh); Jaime Carbonell (CMU, LTI)
  • Evaluating model calibration in classification
    Juozas vaicenavicius (Uppsala University)*; David Widmann (Uppsala University); Carl Andersson (Uppsala University); Fredrik Lindsten (Uppsala University); Jacob Roll (Veoneer Inc.); Thomas Schön (Uppsala University)
  • Towards Gradient Free and Projection Free Stochastic Optimization
    Anit Kumar Sahu (Carnegie Mellon University)*; Manzil Zaheer (Carnegie Mellon University); Soummya Kar ()
  • On Multi-Cause Approaches to Causal Inference with Unobserved Counfounding: Two Cautionary Failure Cases and A Promising Alternative
    Alexander D'Amour (Google Brain)*
  • Data-Driven Approach to Multiple-Source Domain Adaptation
    Petar Stojanov (Carnegie Mellon University)*; Kun Zhang (Carnegie Mellon University); Mingming Gong (University of Pittsburgh); Jaime Carbonell (CMU, LTI)