ICML2019机器学习顶会接受论文列表！

2019 年 5 月 12 日 专知

【导读】2019 第36届机器学习国际会议2019年6月9日至15日美国加州长滩会议中心本年度ICML共收到3400篇左右的投稿，经过严格筛选，共有773篇论文被录用。

https://icml.cc/Conferences/2019/AcceptedPapersInitial

Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization
Thanh Huy Nguyen (Telecom ParisTech) · Umut Simsekli (Telecom ParisTech) · Gaël RICHARD (Télécom ParisTech)

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
Umut Simsekli (Telecom ParisTech) · Levent Sagun (CEA) · Mert Gurbuzbalaban (Rutgers University)

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
Antoine Liutkus (Inria) · Umut Simsekli (Telecom ParisTech) · Szymon Majewski (IMPAN) · Alain Durmus (ENS) · Fabian-Robert Stöter (Inria)

Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth
Jacob Whitehill (Worcester Polytechnic Institute) · Anand Ramakrishnan (Worcester Polytechnic Institute)

Decentralized Exploration in Multi-Armed Bandits
Raphael Feraud (Orange Labs) · REDA ALAMI (Orange Labs - Paris Saclay University - INRIA) · Romain Laroche (Microsoft Research)

Unsupervised Deep Learning by Neighbourhood Discovery
Jiabo Huang (Queen Mary University of London) · Qi Dong (Queen Mary University of London) · Shaogang Gong (Queen Mary University of London) · Xiatian Zhu (Vision Semantics Limited)

Statistical Foundations of Virtual Democracy
Anson Kahng (Carnegie Mellon University) · Min Kyung Lee (CMU) · Ritesh Noothigattu (Carnegie Mellon University) · Ariel Procaccia (Carnegie Mellon University) · Christos-Alexandros Psomas (Carnegie Mellon University)

DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures
Andrew R Lawrence (University of Bath) · Carl Henrik Ek (University of Bristol) · Neill Campbell (University of Bath)

Complexity of Linear Regions in Deep Networks
Boris Hanin (Texas A&M) · David Rolnick (University of Pennsylvania)

Linear-Complexity Data-Parallel Earth Mover's Distance Approximations
Kubilay Atasu (IBM Research - Zurich) · Thomas Mittelholzer (HSR Univ. Applied Sciences, Rapperswil, Switzerland)

Communication Constrained Inference and the Role of Shared Randomness
Jayadev Acharya (Cornell University) · Clement Canonne (Stanford University) · Himanshu Tyagi (IISC)

Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters
Jayadev Acharya (Cornell University) · Ziteng Sun (Cornell University)

Domain Agnostic Learning with Disentangled Representations
Xingchao Peng (Boston University) · Zijun Huang (Columbia University) · Ximeng Sun (Boston University) · Kate Saenko (Boston University)

Sever: A Robust Meta-Algorithm for Stochastic Optimization
Ilias Diakonikolas (USC) · Gautam Kamath (MIT) · Daniel Kane (UCSD) · Jerry Li (MIT) · Jacob Steinhardt (University of California, Berkeley) · Alistair Stewart (University of Southern California)

Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
Tri Dao (Stanford University) · Albert Gu (Stanford University) · Matthew Eichhorn (University at Buffalo) · Atri Rudra (University at Buffalo, SUNY) · Christopher Re (Stanford)

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
Pin-Yu Chen (IBM Research AI) · Lingfei Wu (IBM Research) · Sijia Liu (MIT-IBM Watson AI Lab) · Indika Rajapakse ()

Training Neural Networks with Local Error Signals
Arild Nøkland (Kongsberg Seatex) · Lars Hiller Eidnes (None)

Batch Policy Learning under Constraints
Hoang Le (Caltech) · Cameron Voloshin (Caltech) · Yisong Yue (Caltech)

Exploration Conscious Reinforcement Learning Revisited
Lior Shani (Technion) · Yonathan Efroni (Technion) · Shie Mannor (Technion)

Temporal Gaussian Mixture Layer for Videos
AJ Piergiovanni (Indiana University) · Michael Ryoo (EgoVid / Indiana University)

Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering
Ramakrishna Vedantam (Facebook AI Research) · Karan Desai (Georgia Tech) · Stefan Lee (Georgia Institute of Technology) · Marcus Rohrbach (Facebook AI Research) · Dhruv Batra (Georgia Institute of Technology / Facebook AI Research) · Devi Parikh (Georgia Tech & Facebook AI Research)

Unifying Orthogonal Monte Carlo Methods
Krzysztof Choromanski (Google Brain Robotics) · Mark Rowland (University of Cambridge) · Wenyu Chen (MIT) · Adrian Weller (University of Cambridge, Alan Turing Institute)

TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning
Tameem Adel (University of Cambridge) · Adrian Weller (University of Cambridge, Alan Turing Institute)

SELFIE: Refurbishing Unclean Samples for Robust Deep Learning
Hwanjun Song (KAIST) · Minseok Kim (KAIST) · Jae-Gil Lee (KAIST)

Statistics and Samples in Distributional Reinforcement Learning
Mark Rowland (DeepMind) · Robert Dadashi (Google AI Residency Program) · Saurabh Kumar (Google) · Remi Munos (DeepMind) · Marc Bellemare (Google Brain) · Will Dabney (DeepMind)

Revisiting precision recall definition for generative modeling
Loic Simon (GREYC ENSICAEN) · Ryan Webster (UniCaen) · Julien Rabin (Unicaen)

Action Robust Reinforcement Learning and Applications in Continuous Control
Chen Tessler (Technion) · Yonathan Efroni (Technion) · Shie Mannor (Technion)

Anomaly Detection With Multiple-Hypotheses Predictions
Duc Tam Nguyen (University of Freiburg) · Zhongyu Lou (Bosch) · Michael Klar (Bosch) · Thomas Brox (University of Freiburg)

Band-limited Training and Inference for Convolutional Neural Network
Adam Dziedzic (University of Chicago) · John Paparrizos (University of Chicago) · Sanjay Krishnan (U Chicago) · Aaron Elmore (University of Chicago) · Michael Franklin (University of Chicago)

Greedy Layerwise Learning Can Scale To ImageNet
Eugene Belilovsky (Mila, University of Montreal) · Michael Eickenberg (UC Berkeley) · Edouard Oyallon (CentraleSupélec)

Monge blunts Bayes: Hardness Results for Adversarial Training
Zac Cranko (ANU) · Aditya Menon (Google Research) · Richard Nock (Data61, The Australian National University and the University of Sydney) · Cheng Soon Ong (Data61 and ANU) · Zhan Shi (University of Illinois at Chicago) · Christian Walder (Data61, the Australian National University)

Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits
Martin Zhang (Stanford University) · James Zou (Stanford) · David Tse (Stanford University)

Submodular Cost Submodular Cover with an Approximate Oracle
Victoria Crawford (University of Florida) · Alan Kuhnle (Florida State University) · My T Thai (University of Florida)

Lossless or Quantized Boosting with Integer Arithmetic
Richard Nock (Data61, The Australian National University and the University of Sydney) · Robert C Williamson (ANU)

Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Pengfei Chen (The Chinese University of Hong Kong) · Ben Ben Liao (Tencent) · Guangyong Chen (Tencent) · Shengyu Zhang (Tencent; The Chinese University of Hong Kong)

HexaGAN: Generative Adversarial Nets for Real World Classification
Uiwon Hwang (Seoul National University) · Dahuin Jung (Seoul National University) · Sungroh Yoon (Seoul National University)

Neural Collaborative Subspace Clustering
Tong Zhang (The Australian National University) · Pan Ji (NEC Laboratories America) · Mehrtash Harandi (Monash University) · Wenbing Huang (Tencent AI Lab) · HONGDONG LI (Australian National University, Australia)

Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning
weishi shi (Rochester Institute of Technology) · Qi Yu (Rochester Institute of Technology)

Improved Convergence for $ℓ_{1}$ and $ℓ_{\infty}$ Regression via Iteratively Reweighted Least Squares
Alina Ene (Boston University) · Adrian Vladu (Boston University)

Flat Metric Minimization with Applications in Generative Modeling
Thomas Möllenhoff (TU Munich) · Daniel Cremers (TU Munich)

Learning to Collaborate in Markov Decision Processes
Goran Radanovic (Harvard University) · Rati Devidze (Max Planck Institute for Software Systems) · David Parkes (Harvard University) · Adish Singla (Max Planck Institute (MPI-SWS))

Fast and flexible inference of joint distributions from their marginals
Charles Frogner (MIT) · Tomaso Poggio (Massachusetts Institute of Technology)

Learning Dependency Structures for Weak Supervision Models
Paroma Varma (Stanford University) · Frederic Sala (Stanford) · Ann He (Stanford University) · Alexander J Ratner (Stanford University) · Christopher Re (Stanford)

SWALP : Stochastic Weight Averaging in Low Precision Training
Guandao Yang (Cornell University) · Tianyi Zhang (Cornell University) · Polina Kirichenko (Cornell) · Junwen Bai (Cornell) · Andrew Wilson (Cornell University) · Chris De Sa (Cornell)

Neural Separation of Observed and Unobserved Distributions
Tavi Halperin (Hebrew University of Jerusalem) · Ariel Ephrat (HUJI) · Yedid Hoshen ()

Better generalization with less data using robust gradient descent
Matthew J Holland (Osaka University) · Kazushi Ikeda (Nara Institute of Science and Technology)

Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
Lingbing Guo (Nanjing University) · Zequn Sun (Nanjing University) · Wei Hu (Nanjing University)

Kernel Mean Matching for Content Addressability of GANs
Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems) · Patsorn Sangkloy (Georgia Institution of Technology) · Muhammad Waleed Gondal (Max Planck Institute for Intelligent Systems) · Amit Raj (Georgia Institute of Technology) · James Hays (Georgia Institute of Technology, USA) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Sublinear Sampling for Determinantal Point Processes
Jennifer Gillenwater (Google Research NYC) · Alex Kulesza (Google) · Zelda Mariet (MIT) · Sergei Vassilvitskii (Google)

Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
Natasha Jaques (MIT) · Angeliki Lazaridou (DeepMind) · Edward Hughes (DeepMind) · Caglar Gulcehre (DeepMind) · Pedro Ortega (DeepMind) · DJ Strouse (Princeton University) · Joel Z Leibo (DeepMind) · Nando de Freitas (DeepMind)

Greedy Sequential Subset Selection via Sequential Facility Location
Ehsan Elhamifar (Northeastern University)

TarMAC: Targeted Multi-Agent Communication
Abhishek Das (Georgia Tech) · Theophile Gervet (Carnegie Mellon University) · Joshua Romoff (McGill University) · Dhruv Batra (Georgia Institute of Technology / Facebook AI Research) · Devi Parikh (Georgia Tech & Facebook AI Research) · Michael Rabbat (Facebook) · Joelle Pineau (Facebook)

A Kernel Theory of Modern Data Augmentation
Tri Dao (Stanford University) · Albert Gu (Stanford University) · Alexander J Ratner (Stanford University) · Virginia Smith (Carnegie Mellon University) · Chris De Sa (Cornell) · Christopher Re (Stanford)

Geometry Aware Convolutional Filters for Omnidirectional Images Representation
Renata Khasanova (Ecole Polytechnique Federale de Lausanne (EPFL)) · Pascal Frossard (EPFL)

Convolutional Poisson Gamma Belief Network
CHAOJIE WANG (XIDIAN UNIVERSITY) · Bo Chen (School of Electronic Engineering, Xidian University) · Sucheng Xiao (Xidian University) · Mingyuan Zhou (University of Texas at Austin)

Improving Adversarial Robustness via Promoting Ensemble Diversity
Tianyu Pang (Tsinghua University) · Kun Xu (Tsinghua University) · Chao Du (Tsinghua University) · Ning Chen () · Jun Zhu (Tsinghua University)

Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
Feihu Huang (University of Pittsburgh) · Songcan Chen (Nanjing University of Aeronautics and Astronautics) · Heng Huang (University of Pittsburgh)

Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments
Kirthevasan Kandasamy (Carnegie Mellon University) · Willie Neiswanger (CMU) · Reed Zhang (Carnegie Mellon University) · Akshay Krishnamurthy (Microsoft Research) · Jeff Schneider (Uber/CMU) · Barnabás Póczos (CMU)

Neural Inverse Knitting: From Images to Manufacturing Instructions
Alexandre Kaspar (MIT CSAIL) · Tae-Hyun Oh (MIT CSAIL) · Liane Makatura (MIT) · Petr Kellnhofer (MIT) · Wojciech Matusik (MIT)

Differentially Private Empirical Risk Minimization with Non-convex Loss Functions
Di Wang (State University of New York at Buffalo) · Changyou Chen (SUNY Buffalo) · Jinhui Xu (SUNY Buffalo)

Bayesian Generative Active Deep Learning
Toan Tran (University of Adelaide) · Thanh-Toan Do (The University of Liverpool) · Ian Reid ("University of Adelaide, Australia") · Gustavo Carneiro (University of Adelaide)

Understanding the Origins of Bias in Word Embeddings
Marc-Etienne Brunet (University of Toronto) · Colleen Alkalay-Houlihan (University of Toronto) · Ashton Anderson (University of Toronto) · Richard Zemel (Vector Institute)

GDPP: Learning Diverse Generations using Determinantal Point Processes
Mohamed Elfeki (CRCV) · Camille Couprie (FAIR) · Morgane Riviere (Facebook Artificial Intelligence Research) · Mohamed Elhoseiny (KAUST and Baidu SVAIL)

Multi-Agent Adversarial Inverse Reinforcement Learning
Lantao Yu (Stanford University) · Jiaming Song (Stanford) · Stefano Ermon (Stanford University)

Differentiable Learning to Learn to Normalize
Ping Luo (The University of Hong Kong) · Peng Zhanglin (SenseTime) · Shao Wenqi (CUHK) · Zhang ruimao (cuhk) · Ren jiamin (sensetime) · Wu lingyun (sensetime)

Learning Distance for Sequences by Learning a Ground Metric
Bing Su (Institute of Software, Chinese Academy of Sciences) · Ying Wu (Northwestern University)

Classification from Positive, Unlabeled and Biased Negative Data
Yu-Guan Hsieh (École normale supérieure) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Improved Parallel Algorithms for Density-Based Network Clustering
Mohsen Ghaffari (ETH Zurich) · Silvio Lattanzi (Google Zurich) · Slobodan Mitrović (MIT)

Hierarchically Structured Meta-learning
Huaxiu Yao (Pennsylvania State University) · Ying WEI (Tencent AI Lab) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) · Zhenhui (Jessie) Li (Penn State University)

Nonlinear Distributional Gradient Temporal-Difference Learning
chao qu (Ant Financial Service Group) · Shie Mannor (Technion) · Huan Xu (Georgia Tech)

Differentiable Linearized ADMM
Xingyu Xie (Peking Unversity) · Jianlong Wu (Peking University) · Guangcan Liu (Nanjing University of Information Science and Technology) · Zhisheng Zhong (Peking University) · Zhouchen Lin (Peking University)

Bridging Theory and Algorithm for Domain Adaptation
Yuchen Zhang (Tsinghua University) · Tianle Liu (Tsinghua University) · Mingsheng Long (Tsinghua University) · Michael Jordan (UC Berkeley)

Sublinear Time Nearest Neighbor Search over Generalized Weighted Space
Yifan Lei (National University of Singapore) · Qiang Huang (National University of Singapore) · Mohan Kankanhalli (National University of Singapore,) · Anthony Tung (NUS)

Imitation Learning from Imperfect Demonstration
Yueh-Hua Wu (National Taiwan University) · Nontawat Charoenphakdee (The University of Tokyo / RIKEN) · Han Bao (The University of Tokyo / RIKEN) · Voot Tangkaratt (RIKEN AIP) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Adversarial Online Learning with noise
ALON RESLER (Tel Aviv University) · Yishay Mansour (Google and Tel Aviv University)

Near optimal finite time identification of arbitrary linear dynamical systems
Tuhin Sarkar (MIT) · Alexander Rakhlin (MIT)

Bayesian Joint Spike-and-Slab Graphical Lasso
Zehang Li (Yale School of Public Health) · Tyler Mccormick (University of Washington) · Samuel Clark (The Ohio State University)

Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Axel Abels (Université Libre de Bruxelles) · Diederik Roijers (VUB) · Tom Lenaerts (Vrije Universiteit Brussel) · Ann Nowé (Vrije Universiteit Brussel) · Denis Steckelmacher (Vrije Universiteit Brussel)

The Wasserstein Transform
Facundo Memoli (Ohio State University) · Zane Smith (University of Minnesota) · Zhengchao Wan (The Ohio State University)

Sum-of-Squares Polynomial Flow
Priyank Jaini (University of Waterloo, Vector Institute) · Kira A. Selby (University of Waterloo) · Yaoliang Yu (University of Waterloo)

Graphical-model based estimation and inference for differential privacy
Ryan McKenna (UMass Amherst) · Daniel Sheldon (University of Massachusetts Amherst) · Gerome Miklau (University of Massachusetts, Amherst)

Control Regularization for Reduced Variance Reinforcement Learning
Richard Cheng (California Institute of Technology) · Abhinav Verma (Rice University) · Gabor Orosz (University of Michigan) · Swarat Chaudhuri (Rice University) · Yisong Yue (Caltech) · Joel Burdick (Caltech)

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Kate Rakelly (UC Berkeley) · Aurick Zhou (UC Berkeley) · Chelsea Finn (Stanford, Google, UC Berkeley) · Sergey Levine (Berkeley) · Deirdre Quillen (UC Berkeley)

On Sparse Linear Regression in the Local Differential Privacy Model
Di Wang (State University of New York at Buffalo) · Jinhui Xu (SUNY Buffalo)

Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff
Yochai Blau (Technion) · Tomer Michaeli (Technion)

Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers
Hong Liu (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University) · Michael Jordan (UC Berkeley)

Adaptive Neural Trees
Ryutaro Tanno (University College London) · Kai Arulkumaran (Imperial College London) · Daniel Alexander (University College London) · Antonio Criminisi (Microsoft) · Aditya Nori (Microsoft Research Cambridge)

A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion
Sylvain Lamprier (LIP6 - Sorbonne Universités)

Learning Efficient Feature Augmentation with Non-local Relations for Visual Recognition
Songyang Zhang (ShanghaiTech University) · Xuming He (ShanghaiTech University) · Shipeng Yan (ShanghaiTech University)

Learning Structured Decision Problems with Unawareness
Craig Innes (University of Edinburgh) · Alex Lascarides (University of Edinburgh)

Improving model selection by employing the test data
Max Westphal (University of Bremen) · Werner Brannath (University of Bremen)

CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration
Gellért Weisz (DeepMind) · Andras Gyorgy (DeepMind) · Csaba Szepesvari (DeepMind/University of Alberta)

Dead-ends and Secure Exploration in Reinforcement Learning
Mehdi Fatemi (Microsoft Research) · Shikhar Sharma (Microsoft Research) · Harm van Seijen (Microsoft Research) · Samira Ebrahimi Kahou (Microsoft Research)

The information-theoretic value of unlabeled data in semi-supervised learning
Alexander Golovnev (Harvard) · David Pal (Expedia) · Balazs Szorenyi (Yahoo Research)

Nearest neighbor and kernel survival analysis: Nonasymptotic error bounds and strong consistency rates
George Chen (Carnegie Mellon University)

Recursive Sketches for Modular Deep Learning
Badih Ghazi (Google) · Rina Panigrahy (Google) · Joshua R. Wang (Google)

Off-Policy Deep Reinforcement Learning without Exploration
Scott Fujimoto (McGill University) · David Meger (McGill University) · Doina Precup (McGill University / DeepMind)

GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward Smith (McGill University) · Adriana Romero (FAIR) · Scott Fujimoto (McGill University) · David Meger (McGill University)

Population Random Measure Embedding
Aonan Zhang (Columbia University) · John Paisley (Columbia University)

Learning to Prove Theorems via Interacting with Proof Assistants
Kaiyu Yang (Princeton University) · Jia Deng (Princeton University)

Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
Andrew Cotter (Google AI) · Maya Gupta (Google) · Heinrich Jiang (Google Research) · Nati Srebro (Toyota Technological Institute at Chicago) · Karthik Sridharan (Cornell University) · Serena Wang (Google) · Blake Woodworth (TTI-Chicago) · Seungil You (Kakao Mobility)

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
Dong Yin (UC Berkeley) · Yudong Chen (Cornell University) · Kannan Ramchandran (UC Berkeley) · Peter Bartlett (UC Berkeley)

Rethinking Model Scaling for Deep Convolutional Neural Networks
Mingxing Tan (Google Brain) · Quoc Le (Google Brain)

NATTACK: Improved Black-Box Adversarial Attack with Normal Distributions
Yandong li (University of Central Florida) · Lijun Li (Beihang University) · Liqiang Wang (University of Central Florida) · Tong Zhang (Tencent) · Boqing Gong (Google)

Greedy Orthogonal Pivoting for Non-Negative Matrix Factorization
Kai Zhang (Temple University) · Sheng Zhang (Temple University) · Jun Liu (Infinia ML Inc.) · Jun Wang (Alibaba) · Jie Zhang (Fudan University)

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
Daniel Ho (UC Berkeley) · Eric Liang (UC Berkeley) · Xi Chen (UC Berkeley) · Ion Stoica (UC Berkeley) · Pieter Abbeel (UC Berkeley)

Weak Detection of Signal in the Spiked Wigner Model
Hye Won Chung (KAIST) · Ji Oon Lee (KAIST)

Compressing Gradient Optimizers via Count-Sketches
Ryan Spring (Rice University) · Anastasios Kyrillidis (Rice University) · Vijai Mohan () · Anshumali Shrivastava (Rice University)

Variational Laplace Autoencoders
Yookoon Park (Seoul National University) · Chris Kim (Seoul National University) · Gunhee Kim (Seoul National University)

New results on information theoretic clustering
Ferdinando Cicalese (University of Verona) · Eduardo Laber (PUC-RIO) · Lucas Murtinho (PUC-RJ)

On Medians of (Randomized) Pairwise Means
Stephan Clemencon (Telecom ParisTech) · Pierre Laforgue (Télécom ParisTech) · Patrice Bertail (Université Paris Nanterre)

Molecular Hypergraph Grammar with Its Application to Molecular Optimization
Hiroshi Kajino (MIT-IBM Watson AI Lab / IBM Research)

Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning
Seungyul Han (KAIST) · Youngchul Sung (KAIST)

Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
Alina Beygelzimer (Yahoo Research) · David Pal (Expedia) · Balazs Szorenyi (Yahoo Research) · Devanathan Thiruvenkatachari (New York University) · Chen-Yu Wei (University of Southern California) · Chicheng Zhang (Microsoft Research)

Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
Chicheng Zhang (Microsoft Research) · Alekh Agarwal (Microsoft Research) · Hal Daume (Microsoft Research) · John Langford (Microsoft Research) · Sahand Negahban (YALE)

Weakly-Supervised Temporal Localization via Occurrence Count Learning
Julien Schroeter (Cardiff University) · Kirill Sidorov (Cardiff University) · David Marshall (Cardiff University)

Imputing Missing Events in Continuous-Time Event Streams
Hongyuan Mei (Johns Hopkins University) · Guanghui Qin (Peking University) · Jason Eisner (Johns Hopkins University)

Graph U-Nets
Hongyang Gao (Texas A&M University) · Shuiwang Ji (Texas A&M University)

First-Order Algorithms Converge Faster than $O (1 / k)$ on Convex Problems
Ching-pei Lee (University of Wisconsin-Madison) · Stephen Wright (University of Wisconsin-Madison)

Composing Entropic Policies using Divergence Correction
Jonathan Hunt (DeepMind) · Andre Barreto (DeepMind) · Timothy Lillicrap (Google DeepMind) · Nicolas Heess (DeepMind)

Online Convex Optimization in Adversarial Markov Decision Processes
Aviv Rosenberg (Tell Aviv University) · Yishay Mansour (Google and Tel Aviv University)

On the Convergence and Robustness of Adversarial Training
Yisen Wang (Tsinghua University) · Xingjun Ma (The University of Melbourne) · James Bailey (The University of Melbourne) · Jinfeng Yi (JD AI Research) · Bowen Zhou (JD) · Quanquan Gu (University of California, Los Angeles)

Safe Policy Improvement with Baseline Bootstrapping
Romain Laroche (Microsoft Research) · Paul TRICHELAIR (Mila - Quebec AI Institute/McGill University) · Remi Tachet des Combes (Microsoft Research Montreal)

Variational Inference for sparse network reconstruction from count data
Julien Chiquet (INRA / AgroParisTech / Paris Saclay) · Stephane Robin (INRA / AgroParisTech / Paris Saclay) · Mahendra Mariadassou (INRA)

Simplifying Graph Convolutional Networks
Felix Wu (Cornell University) · Amauri Souza (Cornell University) · Tianyi Zhang (Cornell University) · Christopher Fifty (Cornell University) · Tao Yu (Shanghai Jiao Tong University) · Kilian Weinberger (Cornell University)

Fairness without Harm: Decoupled Classifiers with Preference Guarantees
Berk Ustun (Harvard University) · Yang Liu (UCSC) · David Parkes (Harvard University)

Non-Parametric Priors For Generative Adversarial Networks
Rajhans Singh (Arizona State University) · Pavan Turaga (Arizona State University) · Suren Jayasuriya (Arizona State University) · Ravi Garg (Intel Corporation) · Martin Braun (Intel Corporation)

Stochastic Blockmodels meet Graph Neural Networks
Nikhil Mehta (Duke University) · Lawrence Carin (Duke) · Piyush Rai (IIT Kanpur)

Learning Generative Models across Incomparable Spaces
Charlotte Bunne (ETH) · David Alvarez-Melis (MIT) · Andreas Krause (ETH Zurich) · Stefanie Jegelka (MIT)

Rademacher Complexity for Adversarially Robust Generalization
Dong Yin (UC Berkeley) · Kannan Ramchandran (UC Berkeley) · Peter Bartlett (UC Berkeley)

Accelerated Flow for Probability Distributions
Amirhossein Taghvaei (University of Illinois at Urbana-Champaign) · Prashant Mehta (University of Illinois at Urbana-CHampaign)

Generalized Majorization-Minimization
Sobhan Naderi Parizi (Google Inc.) · Kun He (Facebook Reality Labs) · Reza Aghajani (University of California San Diego) · Stan Sclaroff (Boston University) · Pedro Felzenszwalb (Brown University)

Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization
Kaiyi Ji (The Ohio State University) · Zhe Wang (Ohio State University) · Yi Zhou (Duke University) · Yingbin LIANG (The Ohio State University)

Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization
Hesham Mostafa (Intel Corporation) · Xin Wang (Cerebras Systems)

Metropolis-Hastings Generative Adversarial Networks
Ryan Turner (Uber AI Labs) · Jane Hung (Uber) · Eric Frank (Uber AI Labs) · Yunus Saatchi (Uber AI Labs) · Jason Yosinski (Uber Labs)

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Branislav Kveton (Google Research) · Csaba Szepesvari (DeepMind/University of Alberta) · Sharan Vaswani (Mila, University of Montreal) · Zheng Wen (Adobe Research) · Tor Lattimore (DeepMind) · Mohammad Ghavamzadeh (Facebook AI Research)

Direct Uncertainty Prediction for Medical Second Opinions
Maithra Raghu (Cornell University / Google Brain) · Katy Blumer (Google) · Rory sayres (Google) · Ziad Obermeyer (UC Berkeley School of Public Health) · Bobby Kleinberg (Cornell) · Sendhil Mullainathan (Harvard University) · Jon Kleinberg (Cornell University)

Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model
Gi-Soo Kim (Seoul National University) · Myunghee Cho Paik (Seoul National University)

On Symmetric Losses for Learning from Corrupted Labels
Nontawat Charoenphakdee (The University of Tokyo / RIKEN) · Jongyeong Lee (The University of Tokyo/RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Lipschitz Generative Adversarial Nets
Zhiming Zhou (SJTU) · Jiadong Liang (Peking University) · Yuxuan Song (Shanghai Jiao Tong Univesity) · Lantao Yu (Stanford University) · Hongwei Wang (Shanghai Jiao Tong University) · Weinan Zhang (Shanghai Jiao Tong University) · Yong Yu (Shanghai Jiao Tong University) · Zhihua Zhang (Peking University)

Spectral Clustering of Signed Graphs via Matrix Power Means
Pedro Mercado (Saarland University / University of Tubingen) · Matthias Hein (University of Tübingen) · Francesco Tudisco (University of Strathclyde)

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Samet Oymak (University of California, Riverside) · Mahdi Soltanolkotabi (University of Southern California)

POPCORN: Certifying Robustness of Recurrent Neural Networks
CHING-YUN KO (The University of Hong Kong) · Zhaoyang Lyu (The Chinese University of Hong Kong) · Tsui-Wei Weng (MIT) · Luca Daniel (Massachusetts Institute of Technology) · Ngai Wong (The University of Hong Kong) · Dahua Lin (The Chinese University of Hong Kong)

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Sami Abu-El-Haija (USC Information Sciences Institute) · Bryan Perozzi (Google AI) · Amol Kapoor (Google Research) · Nazanin Alipourfard (University of Southern California) · Kristina Lerman (ISI, University of Southern California) · Hrayr Harutyunyan (University of Southern California) · Greg Ver Steeg (University of Southern California) · Aram Galstyan (USC ISI)

Static Automatic Batching In TensorFlow
Ashish Agarwal (Google Brain)

State-Regularized Recurrent Neural Networks
Cheng Wang (NEC Laboratories Europe) · Mathias Niepert (NEC Laboratories Europe)

Online Adaptive Principal Component Analysis and Its extensions
Jianjun Yuan (University of Minnesota) · Andrew Lamperski (University of Minnesota)

Passed & Spurious: analysing descent algorithms and local minima in spiked matrix-tensor model
Stefano Sarao Mannelli (Institut de Physique Théorique) · Florent Krzakala () · Pierfrancesco Urbani (Institut de Physique Théorique) · Lenka Zdeborova (CEA Saclay)

Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
Mario Lezcano Casado (Univeristy of Oxford) · David Martínez-Rubio (University of Oxford)

Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
Kaichao You (Tsinghua University) · Ximei Wang (Tsinghua University) · Mingsheng Long (Tsinghua University) · Michael Jordan (UC Berkeley)

RaFM: Rank-Aware Factorization Machines
Xiaoshuang Chen (Tsinghua Univerisity) · Yin Zheng (WeChat Search Application Department, Tencent) · Jiaxing Wang (Institute of Automation, Chinese Academy of Sciences) · Wenye Ma (Tencent) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

Overcoming multi-model forgetting
Yassine Benyahia (IPROVA) · Kaicheng Yu (EPFL) · Kamil Bennani-Smires (Swisscom) · Martin Jaggi (EPFL) · Anthony C. Davison (EPFL) · Mathieu Salzmann (EPFL) · Claudiu Musat (Swisscom)

Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization
Michael Metel (RIKEN Center for Advanced Intelligence Project) · Akiko Takeda (The University of Tokyo / RIKEN)

LegoNet: Efficient Convolutional Neural Networks with Lego Filters
Zhaohui Yang (Peking University) · Yunhe Wang (Peking University) · Chuanjian Liu (Huawei Noah's Ark Lab) · Hanting Chen (Peking University) · Chunjing Xu (Huawei Noah's Ark Lab) · Boxin Shi (Peking University) · Chao Xu (Peking University) · Chang Xu (University of Sydney)

更多请到查看

https://icml.cc/Conferences/2019/AcceptedPapersInitial

-END-

专 · 知

专知，专业可信的人工智能知识分发，让认知协作更快更好！欢迎登录www.zhuanzhi.ai，注册登录专知，获取更多AI知识资料！