「最全」机器学习顶会 ICML 2018 接收论文列表

新智元推荐

来源：专知（ID：Quan_Zhuanzhi）

【新智元导读】机器学习领域最具影响力的学术会议之一的ICML将于2018年7月10日-15日在瑞典斯德哥尔摩举行。ICML是机器学习领域顶级会议，由国际机器学习协会（International Machine Learning Society）主办。今年人工智能顶会JCAI2018也将于 7月 13 日 - 7 月 19 日 在瑞典斯德哥尔摩举行，很多人可能同时会参加这两个会议，期待七月份的盛会。

详细录用名单日前已经公布，可参见：https://icml.cc/Conferences/2018/AcceptedPapersInitial

论文列表：

ICML 2018 Accepted Papers

Tempered Adversarial Networks

Mehdi S. M. Sajjadi (Max Planck Institute for Intelligent Systems) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Adaptive Three Operator Splitting

Fabian Pedregosa (UC Berkeley) · Gauthier Gidel (MILA)

INSPECTRE: Privately Estimating the Unseen

Jayadev Acharya (Cornell University) · Gautam Kamath (MIT) · Ziteng Sun (Cornell University) · Huanyu Zhang (Cornell University)

Topological mixture estimation

Steve Huntsman (BAE Systems FAST Labs)

On Nesting Monte Carlo Estimators

Tom Rainforth (University of Oxford) · Rob Cornish (Oxford) · Hongseok Yang (KAIST) · andrew warrington (University of Oxford) · Frank Wood (University of Oxford)

Anonymous Walk Embeddings

SERGEY IVANOV (SKOLTECH & CRITEO) · Evgeny Burnaev (Skoltech)

Do Outliers Ruin Collaboration?

Mingda Qiao (IIIS, Tsinghua University)

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization

Umut Simsekli (Telecom ParisTech) · Cagatay Yildiz (Aalto University) · Than Nguyen (Telecom ParisTech) · Ali Cemgil (Bogazici University) · Gaël RICHARD (Télécom ParisTech)

Variational Network Inference: Strong and Stable with Concrete Support

Amir Dezfouli (UNSW) · Edwin Bonilla (UNSW) · Richard Nock (Data61, The Australian National University and the University of Sydney)

Semi-Supervised Learning on Data Streams via Temporal Label Propagation

Tal Wagner (MIT) · Sudipto Guha (Amazon) · Shiva Kasiviswanathan (Amazon) · Nina Mishra (Amazon)

Learning Diffusion using Hyperparameters

Dimitrios Kalimeris (Harvard University) · Yaron Singer (Harvard) · Karthik Subbian (Facebook) · Udi Weinsberg (Facebook)

Distributional Optimization from Samples

Yaron Singer (Harvard) · Eric Balkanski (Harvard) · Nir Rosenfeld (Harvard University) · Amir Globerson (Tel Aviv University, Google)

Approximation Guarantees for Adaptive Sampling

Eric Balkanski (Harvard) · Yaron Singer (Harvard)

Safe Element Screening for Submodular Function Minimization

Weizhong Zhang (Zhejiang University & Tencent AI Lab) · Bin Hong (Zhejiang University) · Lin Ma (Tencent AI Lab) · Wei Liu (Tencent AI Lab) · Tong Zhang (Tecent AI Lab)

Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis

Pengtao Xie (Carnegie Mellon University) · Wei Wu (Carnegie Mellon University) · Eric Xing (Carnegie Mellon University)

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method

Li Shen (Tencent AI Lab) · Peng Sun (Tencent AI Lab) · Yitong Wang (Tencent AI Lab) · Wei Liu (Tencent AI Lab) · Tong Zhang (Tecent AI Lab)

Nonoverlap-Promoting Variable Selection

Pengtao Xie (Carnegie Mellon University) · Hongbao Zhang (Petuum Inc) · Eric Xing (Carnegie Mellon University)

Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection

Jeremias Knoblauch (Warwick University) · Theodoros Damoulas (University of Warwick)

Improved Training of Generative Adversarial Networks Using Representative Features

Duhyeon Bang (Yonsei univ.) · Hyunjung Shim (Yonsei University)

End-to-end Active Object Tracking via Reinforcement Learning

Wenhan Luo (Tencent AI Lab) · Peng Sun (Tencent AI Lab) · Fangwei Zhong (Peking University) · Wei Liu (Tencent AI Lab) · Tong Zhang (Tecent AI Lab) · Yizhou Wang (Peking University)

Bayesian Quadrature for Multiple Related Integrals

Xiaoyue Xi (Imperial College London) · Francois-Xavier Briol (University of Warwick) · Mark Girolami (Imperial College London)

Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks

Zhihao Jia (Stanford University) · Sina Lin (Microsoft) · Charles Qi (Stanford University) · Alex Aiken (Stanford University)

Theoretical Analysis of Image-to-Image Translation with Adversarial Learning

PAN XUDONG (Fudan University) · Mi Zhang (Fudan University) · Daizong Ding (Fudan University)

Implicit Regularization in Nonconvex Statistical Estimation

Cong Ma (Princeton University) · Kaizheng Wang (Princeton University) · Yuejie Chi (CMU) · Yuxin Chen (Princeton University)

Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy

Jiasen Yang (Purdue University) · Qiang Liu (UT Austin) · Vinayak A Rao (Purdue University) · Jennifer Neville (Purdue University)

An Iterative, Sketching-based Framework for Ridge Regression

Agniva Chowdhury (Purdue University) · Jiasen Yang (Purdue University) · Petros Drineas (Purdue University)

Improving Sign Random Projections With Additional Information

Keegan Kang (Singapore University Of Technology And Design) · Wei Pin Wong (Singapore University of Technology and Design)

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

Bo Zhao (Peking University) · Xinwei Sun (Peking University) · Yanwei Fu (Fudan university) · Yuan Yao (Hong Kong Science Tech) · Yizhou Wang (Peking University)

On the Spectrum of Random Features Maps of High Dimensional Data

Zhenyu Liao (L2S, CentraleSupelec) · Romain Couillet (CentralSupélec)

SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions

chandrajit bajaj (University of Texas at Austin) · Tingran Gao (University of Chicago) · Zihang He (Tsinghua University) · Qixing Huang (The University of Texas at Austin) · Zhenxiao Liang (Tsinghua University)

Which Training Methods for GANs do actually Converge?

Lars Mescheder (MPI Tübingen) · Andreas Geiger (MPI-IS and University of Tuebingen) · Sebastian Nowozin (Microsoft Research)

Neural Photometric Stereo Reconstruction for General Reflectance Surfaces

Tatsunori Taniai (RIKEN AIP) · Takanori Maehara (RIKEN AIP)

Adversarial Learning with Local Coordinate Coding

Jiezhang Cao (South China University of Technology) · Yong Guo (South China University of Technology) · Chunhua Shen (University of Adelaide) · Qingyao Wu (South China University of Technology) · Mingkui Tan (South China University of Technology)

Junction Tree Variational Autoencoder for Molecular Graph Generation

Wengong Jin (MIT Computer Science and Artificial Intelligence Laboratory) · Regina Barzilay (MIT CSAIL) · Tommi Jaakkola (MIT)

DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding

CMLA Thomas Moreau (CMLA, ENS Paris-Saclay) · Laurent Oudre (Universite Paris 13) · CMLA Nicolas Vayatis (CMLA, ENS Paris Saclay)

Gradually Updated Neural Networks for Large-Scale Image Recognition

Siyuan Qiao (Johns Hopkins University) · Zhishuai Zhang (Johns Hopkins University) · Wei Shen (Shanghai University) · Bo Wang (Hikvision Research Institue) · Alan Yuille (Johns Hopkins University)

Blind Justice: Fairness with Encrypted Sensitive Attributes

Niki Kilbertus (MPI Tübingen & Cambridge) · Adria Gascon (The Alan Turing Institute / Warwick University) · Matt Kusner (Alan Turing Institute) · Michael Veale (UCL) · Krishna Gummadi (MPI-SWS) · Adrian Weller (University of Cambridge, Alan Turing Institute)

Structured Evolution with Compact Architectures for Scalable Policy Optimization

Krzysztof Choromanski (Google Brain Robotics) · Mark Rowland (University of Cambridge) · Vikas Sindhwani (Google) · Richard E Turner (University of Cambridge) · Adrian Weller (University of Cambridge, Alan Turing Institute)

Discovering Interpretable Representations for Both Deep Generative and Discriminative Models

Tameem Adel (University of Cambridge) · Zoubin Ghahramani (University of Cambridge & Uber) · Adrian Weller (University of Cambridge, Alan Turing Institute)

Neural Program Synthesis from Diverse Demonstration Videos

Shao-Hua Sun (University of Southern California) · Hyeonwoo Noh (POSTECH) · Sriram Somasundaram (University of Southern California) · Joseph Lim (Univ. of Southern California)

Learning Low-Dimensional Temporal Representations

Bing Su (Institute of Software Chinese Academy of Sciences)

Weakly consistent optimal pricing algorithms in repeated posted-price auctions with strategic buyer

Alexey Drutsa (Yandex; MSU)

Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice

Alan Kuhnle (University of Florida) · J. Smith (University of Florida) · Victoria Crawford (University of Florida) · My Thai (University of Florida)

Learning the Reward Function for a Misspecified Model

Erik Talvitie (Franklin & Marshall College)

Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Big Data and Model Selection

Ibrahim Alabdulmohsin (Saudi Aramco)

Message Passing Stein Variational Gradient Descent

Jingwei Zhuo (Tsinghua University) · Chang Liu (Tsinghua University) · Jiaxin Shi (Tsinghua University) · Jun Zhu (Tsinghua University) · Ning Chen () · Bo Zhang (Tsinghua University)

Towards Binary-Valued Gates for Robust LSTM Training

Di He (Microsoft Research) · Zhuohan Li (Peking University) · Fei Tian (Microsoft Research) · Wei Chen (Microsoft Research) · Tao Qin (Microsoft Research Asia) · Liwei Wang (Peking University) · Tieyan Liu ()

Learning Representations and Generative Models for 3D Point Clouds

Panagiotis Achlioptas (Stanford) · Olga Diamanti (Stanford) · Ioannis Mitliagkas (MILA, UdeM) · Leonidas Guibas (Stanford University)

Parallel Bayesian Network Structure Learning

Tian Gao (IBM Research) · Dennis Wei (IBM Research)

Batched Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design

Wenlong Lyu (Fudan University) · Fan Yang (Fudan University) · Changhao Yan () · Dian Zhou (Department of Electrical Engineering The University of Texas at Dallas Richardso) · Xuan Zeng (Fudan University)

Human Activity Prediction Using Sequence Earley Algorithm

Siyuan Qi (UCLA) · Baoxiong Jia (Peking University) · University of California Yingnian Wu (University of California, Los Angeles) · Song-Chun Zhu (UCLA)

Stochastic Proximal Algorithms for AUC Maximization

Michael Natole Jr (University at Albany) · Yiming Ying (SUNY Albany) · Siwei Lyu (University at Albany, State University of New York)

Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima

Simon Du (Carnegie Mellon University) · Jason Lee (University of Southern California) · Yuandong Tian (Facebook AI Research) · Aarti Singh (Carnegie Mellon University) · Barnabás Póczos (CMU)

Theoretical Insights into the Optimization Landscape and Generalization Ability of Over-parametrized Neural Networks

Simon Du (Carnegie Mellon University) · Jason Lee (University of Southern California)

Coded Sparse Matrix Multiplication

Sinong Wang (The Ohio State University) · Jiashang Liu (The Ohio State University) · Ness Shroff (The Ohio State University)

Invariance of Weight Distributions in Rectified MLPs

Susumu Tsuchida (The University of Queensland) · Fred Roosta (University of Queensland) · Marcus Gallagher (University of Queensland)

Video Prediction with Appearance and Motion Conditions

Yunseok Jang (Seoul National University) · Gunhee Kim (Seoul National University) · Yale Song (Microsoft AI & Research)

Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints

Ehsan Kazemi (Yale) · Morteza Zadimoghaddam (Google) · Amin Karbasi (Yale)

Theoretical Analysis of Sparse Subspace Clustering with Missing Entries

Manolis Tsakiris (Johns Hopkins University) · Rene Vidal (Johns Hopkins University)

Binary Partitions with Approximate Minimum Impurity

Eduardo Laber (PUC-RIO) · Marco Molinaro (PUC-RIO) · Felipe de A. Mello Pereira (Pontifícia Universidade Católica do Rio de Janeiro)

A Riemannian approach for structured low-rank matrix learning

Pratik Kumar Jawanpuria (Microsoft) · Bamdev Mishra (Microsoft)

The Generalization Error of Dictionary Learning with Moreau Envelopes

ALEXANDROS GEORGOGIANNIS (TECHNICAL UNIVERSITY OF CRETE)

Understanding Generalization and Optimization Performance of Deep CNNs

Pan Zhou (National University of Singapore) · Jiashi Feng (National University of Singapore)

Learning Compact Neural Networks with Regularization

Samet Oymak (University of California, Riverside)

PDE-Net: Learning PDEs from Data

Zichao Long (Peking University) · Yiping Lu (Peking University) · Xianzhong Ma (Peking University) · Bin Dong (Peking University)

Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations

Yiping Lu (Peking University) · Aoxiao Zhong (Zhejiang University) · Quanzheng Li (Mass General Hospital, Harvard Medical School) · Bin Dong (Peking University)

Augment and Reduce: Stochastic Inference for Large Categorical Distributions

Francisco Ruiz (Columbia University) · Michalis Titsias (Athens University of Economics and Business) · Adji Bousso Dieng (Columbia University) · David Blei (Columbia University)

Out-of-sample extension of graph adjacency spectral embedding

Keith Levin (University of Michigan) · Fred Roosta (University of Queensland) · Michael Mahoney (UC Berkeley) · Carey Priebe (Johns Hopkins University)

Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks

Brenden Lake (New York University) · Marco Baroni (Facebook Artificial Intelligence Research)

Learn to Exploration with Meta Policy Gradient

Tianbing Xu (Baidu Research, USA) · Jian Peng (UIUC) · Liang Zhao (Baidu Research USA) · Wei Xu (Baidu Research) · Qiang Liu (UT Austin)

Fast Stochastic AUC Maximization with O(1/n)O(1/n)-Convergence Rate

Mingrui Liu (The University of Iowa) · Xiaoxuan Zhang (University of Iowa) · Zaiyi Chen () · Tianbao Yang (The University of Iowa)

An Alternative View: When Does SGD Escape Local Minima?

Bobby Kleinberg (Cornell) · Yuanzhi Li (Princeton University) · Yang Yuan (Cornell University)

Dependent Relational Gamma Process Models for Dynamic Networks

Sikun Yang (TU Darmstadt) · Heinz Koeppl (TU Darmstadt)

Coordinated Exploration in Concurrent Reinforcement Learning

Maria Dimakopoulou (Stanford) · Benjamin Van Roy (Stanford University)

Geodesic Convolutional Shape Optimization

Pierre Baque (EPFL) · Edoardo Remelli (epfl) · Francois Fleuret (Idiap research institute) · EPFL Pascal Fua (EPFL, Switzerland)

Tight Regret Bounds for Bayesian Optimization in One Dimension

Jonathan Scarlett (National University of Singapore)

Active Testing: An Efficient and Robust Framework for Estimating Accuracy

Phuc Nguyen (UC Irvine) · Charless Fowlkes (UC Irvine) · Deva Ramanan (Carnegie Mellon University)

Non-convex Conditional Gradient Sliding

chao qu (technion) · Yan Li (Georgia Institute of Technology) · Huan Xu (Georgia Tech)

Spectrally approximating large graphs with smaller graphs

Andreas Loukas (EPFL) · Pierre Vandergheynst (École polytechnique fédérale de Lausanne)

Quickshift++: Provably Good Initializations for Sample-Based Mean Shift

Heinrich Jiang (Google) · Jennifer Jang (Uber) · Samory Kpotufe (Princeton University)

Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent

Trevor Campbell (MIT) · Tamara Broderick (MIT)

Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow

Xiao Zhang (University of Virginia) · Simon Du (Carnegie Mellon University) · Quanquan Gu (University of Virginia--> UCLA)

Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels

Lu Jiang (Google) · Zhengyuan Zhou (Stanford University) · Thomas Leung (Google Inc) · Li-Jia Li (Google) · Li Fei-Fei (Stanford University & Google)

Adaptive Sampled Softmax with Kernel Based Sampling

Guy Blanc (Stanford University) · Steffen Rendle (Google)

Black Box FDR

Wesley Tansey (Columbia University) · Yixin Wang (Columbia University) · David Blei (Columbia University) · Raul Rabadan (Columbia University Medical Center)

Graphical Nonconvex Optimization for Optimal Estimation in Gaussian Graphical Models

Qiang Sun (University of Toronto) · Kean Tan (University of Minnesota Twin Cities) · Han Liu (Princeton University) · Tong Zhang (Tecent AI Lab)

Policy Optimization with Demonstrations

Bingyi Kang (National University of Singapore) · Jiashi Feng (National University of Singapore)

Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

Jianbo Chen (University of California, Berkeley) · Le Song (Georgia Institute of Technology) · Martin Wainwright (University of California at Berkeley) · Michael Jordan (UC Berkeley)

Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression

Haitao Liu (Rolls-Royce@NTU Corp Lab) · Jianfei Cai (Nanyang Technological University) · Yi Wang (Rolls-Royce Singapore) · Yew Soon ONG (Nanyang Technological University)

The Uncertainty Bellman Equation and Exploration

Brendan O'Donoghue (DeepMind) · Ian Osband (Google DeepMind) · Remi Munos (DeepMind) · Vlad Mnih (Google Deepmind)

Deep Asymmetric Multi-task Feature Learning

Hae Beom Lee (UNIST) · Eunho Yang (KAIST / AItrics) · Sung Ju Hwang (KAIST)

Learning Semantic Representations for Unsupervised Domain Adaptation

Shaoan Xie (Sun Yat-sen University) · Zibin Zheng ()

K-Beam Subgradient Descent for Minimax Optimization

Jihun Hamm (The Ohio State University) · Yung-Kyun Noh (Seoul National University)

Asynchronous Byzantine Machine Learning

Georgios Damaskinos (EPFL) · El Mahdi El Mhamdi (EPFL) · Rachid Guerraoui (EPFL) · Rhicheek Patra (EPFL) · Mahsa Taziki (EPFL)

Differentially Private Database Release via Kernel Mean Embeddings

Matej Balog (University of Cambridge and MPI Tübingen) · Ilya Tosltikhin (Max Planck Institute for Intelligent Systems, Tübingen) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Learning with Abandonment

Ramesh Johari (Stanford University) · Sven Schmit (Stanford University)

Rapid Adaptation with Conditionally Shifted Neurons

Tsendsuren Munkhdalai (Microsoft Research) · Xingdi Yuan (Microsoft Maluuba) · Soroush Mehri (Microsoft Research) · Adam Trischler (Microsoft Research)

PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning

Yunbo Wang (Tsinghua University) · Zhifeng Gao (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University) · Philip Yu (UIC)

The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning

Siyuan Ma (The Ohio State University) · Raef Bassily () · Mikhail Belkin (Ohio State University)

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

Dhruv Malik (UC Berkeley) · Malayandi Palaniappan (UC Berkeley) · Jaime Fisac (UC Berkeley) · Dylan Hadfield-Menell (UC Berkeley) · Stuart Russell (UC Berkeley) · EECS Anca Dragan (EECS Department, University of California, Berkeley)

Dimensionality-Driven Learning with Noisy Labels

Xingjun Ma (The University of Melbourne) · Yisen Wang (Tsinghua University) · Michael E. Houle (National Institute of Informatics) · Shuo Zhou (The University of Melbourne) · Sarah Erfani (University of Melbourne) · Shutao Xia (Tsinghua University) · Sudanthi Wijewickrema (University of Melbourne) · James Bailey (The University of Melbourne)

Rectify Heterogeneous Model with Semantic Mapping

Han-Jia Ye (Nanjing University) · De-Chuan Zhan (Nanjing University) · Yuan Jiang (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

Synthesizing Programs for Images using Reinforced Adversarial Learning

Iaroslav Ganin (Montreal Institute for Learning Algorithms) · Tejas Kulkarni (DeepMind) · Igor Babuschkin () · S. M. Ali Eslami (DeepMind) · Oriol Vinyals (DeepMind)

Fast Information-theoretic Bayesian Optimisation

Binxin Ru (University of Oxford) · Michael A Osborne (U Oxford) · Mark Mcleod (University of Oxford) · Diego Granziol (Oxford)

Local Convergence Properties of SAGA/Prox-SVRG and AccelerationClarice

Poon (University of Cambridge) · Jingwei Liang (University of Cambridge) · Carola Schoenlieb (Cambridge University)

Let’s be honest: An optimal no-regret framework for zero-sum games

Ya-Ping Hsieh (École Polytechnique Fédérale d) · Ehsan Asadi Kangarshahi (University of Cambridge) · Mehmet Fatih Sahin (EPFL) · Volkan Cevher (EPFL)

Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory

Ron Amit (Technion – Israel Institute of Technology) · Ron Meir (Technion Israeli Institute of Technology)

An Estimation and Analysis Framework for the Rasch Model

Andrew Lan (Princeton University) · Mung Chiang (Purdue University) · Christoph Studer (Cornell University)

PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos

Paavo Parmas (Okinawa Institute of Science and Technology Graduate University) · Kenji Doya (Okinawa Institute of Science and Technology) · Carl Rasmussen (-) · Jan Peters (TU Darmstadt + Max Planck Institute for Intelligent Systems)

Comparison-Based Random Forests

Siavash Haghiri (University of Tübingen) · Damien Garreau (Max Planck Institute) · Ulrike von Luxburg (University of Tübingen)

Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks

Peter Bartlett (UC Berkeley) · Dave Helmbold () · Phil Long (Google)

Semi-Amortized Variational Autoencoders

Yoon Kim (Harvard University) · Sam Wiseman (Harvard University) · Andrew Miller (Harvard) · David Sontag (Massachusetts Institute of Technology) · Alexander Rush (Harvard University)

Large-Scale Cox Process Inference using Variational Fourier Features

ST John (PROWLER.io) · James Hensman (PROWLER.io)

Best Arm Identification in Linear Bandits with Linear Dimension Dependency

Chao Tao (Indiana University Bloomington) · Saúl A. Blanco (Indiana University) · Yuan Zhou (Indiana University Bloomington)

Data-Dependent Stability of Stochastic Gradient Descent

Ilja Kuzborskij (University of Milan) · Christoph Lampert (IST Austria)

Learning One Convolutional Layer with Overlapping Patches

Surbhi Goel (University of Texas at Austin) · Adam Klivans (University of Texas at Austin) · Raghu Meka (UCLA)

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Tuomas Haarnoja (UC Berkeley) · Aurick Zhou (UC Berkeley) · Pieter Abbeel (OpenAI / UC Berkeley) · Sergey Levine (Berkeley)

Visualizing and Understanding Atari Agents

Samuel Greydanus (Oregon State University) · Anurag Koul (Oregon State University) · Jonathan Dodge (Oregon State University) · Alan Fern (Oregon State University)

Probabilistic Boolean Tensor Decomposition

Tammo Rukat (University of Oxford) · Christopher Holmes (University of Oxford) · Christopher Yau (University of Birmingham)

Dynamic Regret of Strongly Adaptive Methods

Lijun Zhang (Nanjing University) · Tianbao Yang (The University of Iowa) · rong jin (alibaba group) · Zhi-Hua Zhou (Nanjing University)

Active Learning with Logged Data

Songbai Yan (University of California San Diego) · Kamalika Chaudhuri (University of California at San Diego) · Tara Javidi (University of California San Diego)

Learning to Reweight Examples for Robust Deep Learning

Mengye Ren (Uber ATG / University of Toronto) · Wenyuan Zeng () · Bin Yang (University of Toronto) · Raquel Urtasun (University of Toronto)

An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks

Qianxiao Li (Institute of High Performance Computing, A*STAR, Singapore) · IHPC Shuji Hao (IHPC, A*STAR)

Deep linear networks with arbitrary loss: All local minima are global

Thomas Laurent (Loyola Marymount University) · James von Brecht (CSULB)

Communication Efficient Gradient Coding

Min Ye (Princeton University) · Emmanuel Abbe ()

Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach

Mao Ye (PURDUE UNIVERSITY) · Yan Sun (Purdue University)

Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits

Huasen Wu () · Xueying Guo (University of California Davis) · Xin Liu ()

Composite Marginal Likelihood Methods for Random Utility Models

Zhibing Zhao (Rensselaer Polytechnic Institute) · Lirong Xia (RPI)

Reviving and Improving Recurrent Back-Propagation

Renjie Liao (University of Toronto) · Yuwen Xiong (Uber ATG / University of Toronto) · Ethan Fetaya (University of Toronto) · Lisa Zhang (University of Toronto) · KiJung Yoon (The University of Texas at Austin) · Zachary S Pitkow (Baylor College of Medicine / Rice University) · Raquel Urtasun (University of Toronto) · Richard Zemel (Vector Institute)

Accelerated Spectral Ranking

Arpit Agarwal (University of Pennsylvania) · Prathamesh Patil (University of Pennsylvania) · Shivani Agarwal (University of Pennsylvania)

Dropout Training, Data-dependent Regularization, and Generalization Bounds

Wenlong Mou (UC Berkeley) · Yuchen Zhou (University of Wisconsin, Madison) · Jun Gao (Peking University) · Liwei Wang (Peking University)

Unbiased Objective Estimation in Predictive Optimization

Shinji Ito (NEC Corporation) · Akihiro Yabe (NEC Corporation) · Ryohei Fujimaki (-)

Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients

Lukas Balles (Max Planck Institute for Intelligent Systems) · Philipp Hennig (Max Planck Institute)

An Efficient Semismooth Newton based Algorithm for Convex Clustering

Yancheng Yuan (National University of Singapore) · Defeng Sun (The Hong Kong Polytechnic University) · Kim-Chuan Toh (National University of Singapre)

Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator

Stephen Tu (UC Berkeley) · Benjamin Recht (Berkeley)

The Multilinear Structure of ReLU Networks

Thomas Laurent (Loyola Marymount University) · James von Brecht (CSULB)

Learning long term dependencies via Fourier recurrent units

Jiong Zhang (University of Texas at Austin) · Yibo Lin (UT-Austin) · Zhao Song (UT-Austin) · Inderjit Dhillon (UT Austin & Amazon)

Detecting non-causal artifacts in multivariate linear regression models

Dominik Janzing (Amazon Research Tübingen) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Importance Weighted Transfer of Samples in Reinforcement Learning

Andrea Tirinzoni (Politecnico di Milano) · Andrea Sessa (Politecnico di Milano) · Matteo Pirotta (SequeL - Inria Lille - Nord Europe) · Marcello Restelli (Politecnico di Milano)

On Discrete-Continuous Mixtures in Probabilistic Programming: the Extended Semantics and General Inference Algorithms

Yi Wu (UC Berkeley) · Siddharth Srivastava (Arizona State University) · Nicholas Hay () · Simon Du (Carnegie Mellon University) · Stuart Russell (UC Berkeley)

SADAGRAD: Strongly Adaptive Stochastic Gradient Methods

Zaiyi Chen (University of Science and Technology of China) · Yi Xu (The University of Iowa) · Enhong Chen (University of Science and Technology of China) · Tianbao Yang (The University of Iowa)

Optimization Landscape and Expressivity of Deep CNNs

Quynh Nguyen (Saarland University) · Matthias Hein (University of Tuebingen)

Composite Functional Gradient Learning of Generative Adversarial Models

Rie Johnson (RJ Research Consulting) · Tong Zhang (Tecent AI Lab)

Learning Dynamics of Linear Denoising Autoencoders

Arnu Pretorius (Stellenbosch University) · Steve Kroon (Stellenbosch University) · Herman Kamper (Stellenbosch University)

Noise2Noise: Learning Image Restoration without Clean Training Images

Samuli Laine (NVIDIA Research) · Timo Aila (NVIDIA Research) · Jaakko Lehtinen (Aalto University & NVIDIA) · Tero Karras (NVidia) · Jacob Munkberg (NVIDIA) · Jon Hasselgren (NVIDIA) · Miika Aittala (MIT)

Learning Localized Spatio-Temporal Models From Streaming Data

Muhammad Osama (Uppsala University) · Dave Zachariah (Uppsala University) · Thomas Schön (Uppsala University)

A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates

Kaiwen Zhou (The Chinese University of Hong Kong) · Fanhua Shang (The Chinese University of Hong Kong) · James Cheng (CUHK)

Katyusha X: Simple Momentum Method for Stochastic Sum-of-Nonconvex Optimization

Zeyuan Allen-Zhu (Microsoft Research AI)

Clipped Action Policy Gradient

Yasuhiro Fujita (Preferred Networks, Inc.) · Shin-ichi Maeda (Preferred Networks, inc.)

Revealing Common Behaviors in Heterogeneous Populations

Andrey Zhitnikov (Technion) · Rotem Mulayoff (Technion) · Tomer Michaeli (Technion)

A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks

Okuno Akifumi (Kyoto University; RIKEN AIP) · Tetsuya Hada (Recruit Technologies Co. Ltd.) · Hidetoshi Shimodaira (Kyoto University / RIKEN AIP)

Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks

Daphna Weinshall (Hebrew University of Jerusalem, Israel) · Gad Cohen (Hebrew University)

Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines

Bin Gu (University of Pittsburgh) · Zhouyuan Huo (University of Pittsburgh) · Heng Huang (University of Pittsburgh)

The Dynamics of Learning: A Random Matrix Approach

Zhenyu Liao (L2S, CentraleSupelec) · Romain Couillet (CentralSupélec)

Stability and Generalization of Learning Algorithms that Converge to Global Optima

Zachary Charles (University of Wisconsin-Madison) · Dimitris Papailiopoulos (ECE at University of Wisconsin-Madison)

GAIN: Missing Data Imputation using Generative Adversarial Nets

Jinsung Yoon (University of California, Los Angeles) · James Jordon (University of Oxford) · Mihaela van der Schaar (University of Oxford)

To Understand Deep Learning We Need to Understand Kernel Learning

Mikhail Belkin (Ohio State University) · Siyuan Ma (The Ohio State University) · Soumik Mandal ()

RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks

Jinsung Yoon (University of California, Los Angeles) · James Jordon (University of Oxford) · Mihaela van der Schaar (University of Oxford)

Fast Approximate Spectral Clustering for Dynamic Networks

Lionel Martin (EPFL) · Andreas Loukas (EPFL) · Pierre Vandergheynst (École polytechnique fédérale de Lausanne)

Attention-based Deep Multiple Instance Learning

Maximilian Ilse (University of Amsterdam) · Jakub Tomczak (University of Amsterdam) · Max Welling (University of Amsterdam)

The Mechanics of n-Player Differentiable Games

David Balduzzi (DeepMind) · Sebastien Racaniere (DeepMind) · James Martens (DeepMind) · Jakob Foerster (University of Oxford) · Karl Tuyls (Deepmind) · Thore Graepel (DeepMind)

Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?

Lin Chen (Yale University) · Moran Feldman (The Open University of Israel) · Amin Karbasi (Yale)

Spotlight: Optimizing Device Placement for Training Deep Neural Networks

Yuanxiang Gao (University of Toronto) · Department of Electrical and Computer Li Chen (Department of Electrical and Computer Engineering, University of Toronto) · Baochun Li (University of Toronto)

Spurious Local Minima are Common in Two-Layer ReLU Neural Networks

Itay Safran (Weizmann Institute of Science) · Ohad Shamir (Weizmann Institute of Science)

Black-box Variational Inference for Stochastic Differential Equations

Tom Ryder (Newcastle University) · Andrew Golightly (Newcastle University) · Stephen McGough (Newcastle University) · Dennis Prangle (Newcastle University)

Approximation Algorithms for Cascading Prediction Models

Matthew Streeter (Google)

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

Ronan Fruit (Inria Lille Nord-Europe) · Matteo Pirotta (SequeL - Inria Lille - Nord Europe) · Alessandro Lazaric (FAIR) · Ronald Ortner (Montanuniversitaet Leoben)

Nonconvex Optimization for Fair Regression

Junpei Komiyama (U-Tokyo) · Akiko Takeda (The Institute of Statistical Mathematics) · Junya Honda (University of Tokyo / RIKEN) · Hajime Shimao (Purdue University)

Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

Jiong Zhang (University of Texas at Austin) · Qi Lei (University of Texas at Austin) · Inderjit Dhillon (UT Austin & Amazon)

Bayesian Uncertainty Estimation for Batch Normalized Deep Networks

Mattias Teye (Electronic Arts) · Hossein Azizpour (KTH) · Kevin Smith (KTH Royal Institute of Technology)

由于微信字数限制，部分文章信息没有展示，详情请查看：

https://icml.cc/Conferences/2018/AcceptedPapersInitial