NeurlPS 2019 专知荟萃

企业成果汇总

1. 英特尔AI成果汇总
2. Google AI成果汇总
3. Apple 成果汇总
4. doc.ai成果汇总
5. 阿里巴巴报告
6. 百度-飞桨平台
7. Facebook
8. Microsoft research
9. habana

报告

1. Naman Agarwal ,Elad Hazan ,Karan Singh Logarithmic Regret for Online Control
2. Maxence Ernoult ,Benjamin Scellier,Yoshua Bengio,Damien Querlioz, Julie Grollier Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input
3. Rahul Singh, Maneesh Sahan,Arthur Gretton,Kernel Instrumental Variable Regression
4. Vaishnavh Nagarajan, J. Zico Kolter,Uniform convergence may be unable to explain generalization in deep learning
5. Clarice Poon ,Jingwei Liang, Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration
6. Ruoxi Sun,Ian Kinsella,Scott Linderman,Liam Paninski, Scalable Bayesian inference of dendritic voltage via spatiotemporal recurrent state space models
7. Pim de Haan,Dinesh Jayaraman, Sergey Levine, Causal Confusion in Imitation Learning
8. Anna Wigren ,Riccardo Sven Risuleo, Lawrence Murray,Fredrik Lindsten, Parameter elimination in particle Gibbs sampling
9. Alaa Maalouf ,Ibrahim Jubran, Dan Feldman Fast and Accurate Least-Mean-Squares Solvers
10. Vincent Sitzmann ,Michael Zollhoefer ,Gordon Wetzstein, Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
11. Zijun Gao,Yanjun Han,Zhimei Ren,Zhengqing Zhou Batched Multi-armed Bandits Problem
12. Debmalya Mandal ,Ariel Procaccia,Nisarg Shah,David Woodruff Efficient and Thrifty Voting by Any Means Necessary
13. Sebastian Goldt ,Madhu Advani ,Andrew Saxe , Florent Krzakala ,Lenka Zdeborová Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
14. Joshua Tobin, Wojciech Zaremba ,Pieter Abbeel Geometry-Aware Neural Rendering
15. Ilias Diakonikolas ,Themis Gouleakis ,Christos Tzamos Distribution-Independent PAC Learning of Halfspaces with Massart Noise
16. Andrew Cotter ,Maya Gupta , Harikrishna Narasimhan On Making Stochastic Classifiers Deterministic
17. Yair Carmon ,Yujia Jin ,Aaron Sidford ,Kevin Tian Variance Reduction for Matrix Games
18. Cheng Tang Exponentially convergent stochastic k-PCA without variance reduction
19. Harikrishna Narasimhan, Andrew Cotter ,Maya Gupta Optimizing Generalized Rate Metrics with Three Players
20. Meena Jagadeesan Understanding Sparse JL for Feature Hashing
21. Jonas Kubilius,Martin Schrimpf , Ha Hong , Najib Majaj ,Rishi Rajalingham ,Elias Issa , Kohitij Kar ,Pouya Bashivan, Jonathan Prescott-Roy, Kailyn Schmidt , Aran Nayebi ,Daniel Bear ,Daniel Yamins ,James J DiCarlo Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
22. Saeed Sharifi-Malvajerdi , Michael Kearns , Aaron Roth Average Individual Fairness: Algorithms, Generalization and Experiments
23. Jerome Revaud,Cesar De Souza, Martin Humenberger, Philippe Weinzaepfel R2D2: Reliable and Repeatable Detector and Descriptor
24. Anish Agarwal ,Devavrat Shah,Dennis Shen ,Dogyoon Song On Robustness of Principal Component Regression

教程

• Uber AI 《元学习meta-learning》教程：How Meta-Learning Could Help Us Accomplish Our Grandest AI Ambitions, and Early, Exotic Steps in that Direction
• 微软强化学习教程：Rinforcement Learning: Past, Present, and Future Perspectives
• 麻省理工深度学习教程： Efficient Processing of Deep Neural Networks: from Algorithms to Hardware Architectures
• Yoshua Bengio演讲：From System 1 Deep Learning to System 2 Deep Learning

奖项

• 经典论文奖：Lin Xiao:Dual Averaging Method for Regularized Stochastic Learning and Online Optimization NIPS 2009: 2116-2124

• 杰出新方向论文奖:Uniform convergence maybe unable to explain generalization in deep learning

• 最佳论文：Ilias Diakonikolas, Themis Gouleakis, Christos Tzamos:Distribution-Independent PAC Learning of Halfspaces with Massart Noise

接收论文

理论

• Su Young Lee, Sung-Ik Choi, Sae-Young Chung: Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update

• Xiuyuan Lu, Benjamin Van Roy:Information-Theoretic Confidence Bounds for Reinforcement Learning

• Zihan Zhang, Xiangyang Ji:Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function

• Simon Ramstedt, Christopher J. Pal:Real-Time Reinforcement Learning

• Ming Yu, Zhuoran Yang, Mladen Kolar, Zhaoran Wang:Convergent Policy Optimization for Safe Reinforcement Learning

• Nathan Kallus, Masatoshi Uehara:Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning

• Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taïga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle:A Geometric Perspective on Optimal Representations for Reinforcement Learning

• Harsh Gupta, R. Srikant, Lei Ying:Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning

• Ben Deverett, Ryan Faulkner, Meire Fortunato, Greg Wayne, Joel Z. Leibo:Interval Timing in Deep Reinforcement Learning Agents

• Erwan Lecarpentier, Emmanuel Rachelson:Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning

• Budgeted Reinforcement Learning in Continuous State Space

• Marginalized Off-Policy Evaluation for Reinforcement Learning

• Wenjie Shi, Shiji Song, Hui Wu, Ya-Chu Hsu, Cheng Wu, Gao Huang:Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

• Yonathan Efroni, Nadav Merlis, Mohammad Ghavamzadeh, Shie Mannor:Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

• Sobhan Miryoosefi, Kianté Brantley, Hal Daumé III, Miroslav Dudík:Reinforcement Learning with Convex Constraints

• Bastian Alt, Adrian Sosic, Heinz Koeppl:Correlation Priors for Reinforcement Learning

• Yuzhe Ma, Xuezhou Zhang, Wen Sun, Xiaojin Zhu:Policy Poisoning in Batch Reinforcement Learning and Control

• Abhinav Verma, Hoang Minh Le, Yisong Yue, Swarat Chaudhuri:Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning

强化学习技巧

• The Option Keyboard: Combining Skills in Reinforcement Learning
• Hado van Hasselt, Matteo Hessel, John Aslanides:When to use parametric models in reinforcement learning?
• Jack Umenberger, Mina Ferizbegovic, Thomas B. Schön, Håkan Hjalmarsson:Robust exploration in linear quadratic reinforcement learning

框架

• A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
• Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner, Shimon Whiteson:A Variational Inference Framework for Reinforcement Learning
• Mahmoud Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau, Mike Rabbat:Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

探索和利用

• Lantao Yu, Tianhe Yu, Chelsea Finn, Stefano Ermon:Explicit Planning for Efficient Exploration in Reinforcement Learning

元强化学习

• Francisco M. Garcia, Philip S. Thomas:A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning
• Unsupervised Curricula for Visual Meta-Reinforcement Learning
• Lantao Yu, Tianhe Yu, Chelsea Finn, Stefano Ermon:Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

分层强化学习

• Siyuan Li, Rui Wang, Minxue Tang, Chongjie Zhang:Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
• Yiding Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn:Language as an Abstraction for Hierarchical Deep Reinforcement Learning(Google)

逆强化学习

• Sebastian Tschiatschek, Ahana Ghosh, Luis Haug, Rati Devidze, Adish Singla:Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
• Abi Komanduru, Jean Honorio:On the Correctness and Sample Complexity of Inverse Reinforcement Learning

多智能体

• Chao Qu, Shie Mannor, Huan Xu, Yuan Qi, Le Song, Junwu Xiong:Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
• Sai Qian Zhang, Qi Zhang, Jieyu Lin:Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
• Nicolas Carion, Gabriel Synnaeve, Alessandro Lazaric, Nicolas Usunier:A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning
• Jakob N. Foerster, Christian A. Schröder de Witt, Gregory Farquhar, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson:Multi-Agent Common Knowledge Reinforcement Learning

奖励函数

• Zichuan Lin, Li Zhao, Derek Yang, Tao Qin, Guangwen Yang, Tie-Yan Liu:Distributional Reward Decomposition for Reinforcement Learning

应用

• Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling

其他

• Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann:Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
• Harm van Seijen, Mehdi Fatemi, Arash Tavakoli:Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
• Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine:Search on the Replay Buffer: Bridging Planning and Reinforcement Learnin
• Yingdong Lu, Mark S. Squillante, Chai Wah Wu:A Family of Robust Stochastic Operators for Reinforcement Learning