July 18, 2021 – July 24, 2021

Microsoft at ICML 2021

Lieu: Virtual

Toutes les heures sont en PDT (UTC -7)

05:00 – 09:30 Workshop

Real World RL: Azure Personalizer & Vowpal Wabbit

John Langford, Sheetal Lahabar, Etienne Kintzler, Mark Rucker, Bogdan Mazoure, Qingyun Wu, Pavithra Srinath, Jack Gerrits, Olga Vrousgou, Eduardo Salinas
08:00 – 09:00 Talk

Cool Moves: Decoupling Physical Motions and Self-avatar Motions in Virtual Reality

Eyal Ofek

08:00 – 11:00 Tutorial

Responsible AI in Industry: Practical Challenges and Lessons Learned

Krishnaram Kenthapadi, Ben Packer, Mehrnoosh Sameki, Nashlie Sephus
12:00 – 03:00 Tutorial

Social Implications of Large Language Models

Hal Daume III, Kate Crawford
20:00 – 23:00 Tutorial

Privacy in learning: Basics and the interplay

Huishuai Zhang, Wei Chen

05:20 – 05:25 Talk

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
Publications connexes
- Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
  
  Sam Devlin, Raluca Stevenson, Ida Momennejad, Jaroslaw Rzepecki, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ali Shaw, Katja Hofmann
05:25 – 05:35 Talk

Dataset Dynamics via Gradient Flows in Probability Space
Publications connexes
- Dataset Dynamics via Gradient Flows in Probability Space
  
  David Alvarez-Melis, Nicolo Fusi
05:30 – 05:35 Talk

Exploiting structured data for learning contagious diseases under incomplete testing
Publications connexes
- Exploiting structured data for learning contagious diseases under incomplete testing
  
  Maggie Makar, Lauren R West, David C Hooper, Eric Horvitz, Erica Shenoy, John Guttag
05:35 – 05:40 Talk

Evolving Attention with Residual Convolutions
Publications connexes
- Evolving Attention with Residual Convolutions
  
  Yujing Wang, Yaming Yang, Jiangang Bai, Mingliang Zhang, Jing Bai, Jing Yu, Ce Zhang, Gao Huang, Yunhai Tong
06:20 – 06:25 Talk

Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
Publications connexes
- Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
  
  Shumao Zhang, Pengchuan Zhang, Thomas Hou
06:35 – 06:40 Talk

Acceleration via Fractal Learning Rate Schedules
Publications connexes
- Acceleration via Fractal Learning Rate Schedules
  
  Naman Agarwal, Surbhi Goel, Cyril Zhang
07:20 – 07:25 Talk

Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
Publications connexes
- Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
  
  Jack Kosaian, Amar Phanishayee, Matthai Philipose, Debadeepta Dey, Rashmi Vinayak
07:45 – 07:50 Talk

Interactive Learning from Activity Description
Publications connexes
- Interactive Learning from Activity Description
  
  Khanh Nguyen, Dipendra Misra, Robert E. Schapire, Miro Dudík, Patrick Shafto
08:00 – 09:00 Poster session

Poster Session 1
Publications connexes
- Dataset Dynamics via Gradient Flows in Probability Space
  
  David Alvarez-Melis, Nicolo Fusi
- Evolving Attention with Residual Convolutions
  
  Yujing Wang, Yaming Yang, Jiangang Bai, Mingliang Zhang, Jing Bai, Jing Yu, Ce Zhang, Gao Huang, Yunhai Tong
- Exploiting structured data for learning contagious diseases under incomplete testing
  
  Maggie Makar, Lauren R West, David C Hooper, Eric Horvitz, Erica Shenoy, John Guttag
- Interactive Learning from Activity Description
  
  Khanh Nguyen, Dipendra Misra, Robert E. Schapire, Miro Dudík, Patrick Shafto
- Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
  
  Shumao Zhang, Pengchuan Zhang, Thomas Hou
- Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
  
  Sam Devlin, Raluca Stevenson, Ida Momennejad, Jaroslaw Rzepecki, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ali Shaw, Katja Hofmann
- Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
  
  Jack Kosaian, Amar Phanishayee, Matthai Philipose, Debadeepta Dey, Rashmi Vinayak
- Acceleration via Fractal Learning Rate Schedules
  
  Naman Agarwal, Surbhi Goel, Cyril Zhang
17:20 – 17:25 Talk

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Publications connexes
- Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
  
  Wenxiao Wang, Minghao Chen, Shuai Zhao, Long Chen, Jinming Hu, Hai Liu, Deng Cai, Xiaofei He, Wei Liu
17:25 – 17:30 Talk

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
Publications connexes
- Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
  
  Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Honglak Lee, Mehdi Fatemi
17:45 – 17:50 Talk

Poolingformer: Long Document Modeling with Pooling Attention
Publications connexes
- Poolingformer: Long Document Modeling with Pooling Attention
  
  Hang Zhang, Yeyun Gong, Yelong Shen, Weisheng Li, Jiancheng Lv, Nan Duan, Wei Chen
18:00 – 18:20 Talk

Network Inference and Influence Maximization from Samples
Publications connexes
- Network Inference and Influence Maximization from Samples
  
  Wei Chen, Xiaoming Sun, Jialin Zhang, Zhijie Zhang
18:20 – 18:25 Talk

Dueling Convex Optimization
Publications connexes
- Dueling Convex Optimization
  
  Aadirupa Saha, Tomer Koren, Yishay Mansour
18:35 – 18:40 Talk

Temporally Correlated Task Scheduling for Sequence Learning
Publications connexes
- Temporally Correlated Task Scheduling for Sequence Learning
  
  Xueqing Wu, Lewen Wang, Yingce Xia, Weiqing Liu, Lijun Wu, Shufang Xie, Tao Qin, Tie-Yan Liu
19:25 – 19:30 Talk

Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
Publications connexes
- Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
  
  Aadirupa Saha, Nagarajan Natarajan, Praneeth Netrapalli, Prateek Jain
19:25 – 19:30 Talk

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Publications connexes
- GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
  
  Tianle Cai, Shengjie Luo, Keyulu Xu, Di He, Tie-Yan Liu, Liwei Wang
19:35 – 19:40 Talk

1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Publications connexes
- 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
  
  Hanlin Tang, Shaoduo Gan, Ammar Ahmad Awan, Samyam Rajbhandari, Conglong Li, Xiangru Lian, Ji Liu, Ce Zhang, Yuxiong He
19:40 – 19:45 Talk

Neural Pharmacodynamic State Space Modeling
Publications connexes
- Neural Pharmacodynamic State Space Modeling
  
  Zeshan Hussain, Rahul Gopal Krishnan, David Sontag
20:00 – 21:00 Poster session

Poster Session 2
Publications connexes
- GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
  
  Tianle Cai, Shengjie Luo, Keyulu Xu, Di He, Tie-Yan Liu, Liwei Wang
- Network Inference and Influence Maximization from Samples
  
  Wei Chen, Xiaoming Sun, Jialin Zhang, Zhijie Zhang
- Neural Pharmacodynamic State Space Modeling
  
  Zeshan Hussain, Rahul Gopal Krishnan, David Sontag
- Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
  
  Aadirupa Saha, Nagarajan Natarajan, Praneeth Netrapalli, Prateek Jain
- Poolingformer: Long Document Modeling with Pooling Attention
  
  Hang Zhang, Yeyun Gong, Yelong Shen, Weisheng Li, Jiancheng Lv, Nan Duan, Wei Chen
- Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
  
  Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Honglak Lee, Mehdi Fatemi
- Temporally Correlated Task Scheduling for Sequence Learning
  
  Xueqing Wu, Lewen Wang, Yingce Xia, Weiqing Liu, Lijun Wu, Shufang Xie, Tao Qin, Tie-Yan Liu
- 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
  
  Hanlin Tang, Shaoduo Gan, Ammar Ahmad Awan, Samyam Rajbhandari, Conglong Li, Xiangru Lian, Ji Liu, Ce Zhang, Yuxiong He
- Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
  
  Wenxiao Wang, Minghao Chen, Shuai Zhao, Long Chen, Jinming Hu, Hai Liu, Deng Cai, Xiaofei He, Wei Liu

01:45 – 07:00 Workshop

Women in Machine Learning (WiML) Un-Workshop

Ehi Nosakhare, Wenshuo Guo, Arushi Majha, Amy Zhang, Nezihe Merve Gürel, Audrey Durand, Christina Papadimitriou, Sarah Poole, Tatjana Chavdarova
05:20 – 05:25 Talk

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
Publications connexes
- SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
  
  Kunal Dahiya, Ananye Agarwal, Deepak Saini, Gururaj K, Jian Jiao, Amit Singh, Sumeet Agarwal, Purushottam Kar, Manik Varma
06:20 – 06:25 Talk

How could Neural Networks understand Programs?
Publications connexes
- How could Neural Networks understand Programs
  
  Dinglan Peng, Shuxin Zheng, Yatao Li, Guolin Ke, Di He, Tie-Yan Liu
06:25 – 06:30 Talk

Joint Online Learning and Decision-making via Dual Mirror Descent
Publications connexes
- Joint Online Learning and Decision-making via Dual Mirror Descent
  
  Alfonso Lobos, Paul Grigas, Zheng Wen
06:40 – 06:45 Talk

ChaCha for Online AutoML
Publications connexes
- ChaCha for Online AutoML
  
  Qingyun Wu, Chi Wang, John Langford, Paul Mineiro, Marco Rossi
08:00 – 09:00 Poster session

Poster Session 3
Publications connexes
- How could Neural Networks understand Programs
  
  Dinglan Peng, Shuxin Zheng, Yatao Li, Guolin Ke, Di He, Tie-Yan Liu
- Incentivizing Compliance with Algorithmic Instruments
  
  Dung Ngo, Logan Stapleton, Vasilis Syrgkanis, Steven Wu
- SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
  
  Kunal Dahiya, Ananye Agarwal, Deepak Saini, Gururaj K, Jian Jiao, Amit Singh, Sumeet Agarwal, Purushottam Kar, Manik Varma
- TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
  
  Clément Romac, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer
- Joint Online Learning and Decision-making via Dual Mirror Descent
  
  Alfonso Lobos, Paul Grigas, Zheng Wen
- ChaCha for Online AutoML
  
  Qingyun Wu, Chi Wang, John Langford, Paul Mineiro, Marco Rossi
17:00 – 17:20 Talk

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Publications connexes
- The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
  
  Bohan Wang, Qi Meng, Wei Chen, Tie-Yan Liu
17:25 – 17:30 Talk

Confidence-Budget Matching for Sequential Budgeted Learning
Publications connexes
- Confidence-Budget Matching for Sequential Budgeted Learning
  
  Yonathan Efroni, Nadav Merlis, Aadirupa Saha, Shie Mannor
17:25 – 17:30 Talk

Adversarial Dueling Bandits
Publications connexes
- Adversarial Dueling Bandits
  
  Aadirupa Saha, Tomer Koren, Yishay Mansour
17:35 – 17:40 Talk

TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Publications connexes
- TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
  
  Clément Romac, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer
18:25 – 18:30 Talk

Feature Learning in Infinite-Width Neural Networks
Publications connexes
- Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
  
  Greg Yang, Edward J. Hu
18:35 – 18:40 Talk

Interaction-Grounded Learning
Publications connexes
- Interaction-Grounded Learning
  
  Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad
18:40 – 18:45 Talk

Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
Publications connexes
- Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
  
  Greg Yang, Etai Littwin
18:45 – 18:50 Talk

Incentivizing Compliance with Algorithmic Instruments
Publications connexes
- Incentivizing Compliance with Algorithmic Instruments
  
  Dung Ngo, Logan Stapleton, Vasilis Syrgkanis, Steven Wu
19:00 – 19:20 Talk

Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Publications connexes
- Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
  
  Xutong Liu, Jinhang Zuo, Xiaowei Chen, Wei Chen, John C. S. Lui
19:30 – 19:35 Talk

Provably Correct Optimization and Exploration with Non-linear Policies
Publications connexes
- Provably Correct Optimization and Exploration with Non-linear Policies
  
  Fei Feng, Wotao Yin, Alekh Agarwal, Lin Yang
19:35 – 19:40 Talk

Safe Reinforcement Learning Using Advantage-Based Intervention
Publications connexes
- Safe Reinforcement Learning Using Advantage-Based Intervention
  
  Nolan Wagener, Byron Boots, Ching-An Cheng
20:00 – 21:00 Poster session

Poster Session 4
Publications connexes
- Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
  
  Xutong Liu, Jinhang Zuo, Xiaowei Chen, Wei Chen, John C. S. Lui
- Provably Correct Optimization and Exploration with Non-linear Policies
  
  Fei Feng, Wotao Yin, Alekh Agarwal, Lin Yang
- Safe Reinforcement Learning Using Advantage-Based Intervention
  
  Nolan Wagener, Byron Boots, Ching-An Cheng
- The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
  
  Bohan Wang, Qi Meng, Wei Chen, Tie-Yan Liu
- Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
  
  Greg Yang, Edward J. Hu
- Interaction-Grounded Learning
  
  Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad
- Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
  
  Greg Yang, Etai Littwin

05:20 – 05:25 Talk

Memory-Efficient Pipeline-Parallel DNN Training
Publications connexes
- Memory-Efficient Pipeline-Parallel DNN Training
  
  Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, Xie Chen, Matei Zaharia
05:45 – 05:50 Talk

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
Publications connexes
- Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
  
  Shengyang Sun, Jiaxin Shi, Andrew Wilson, Roger Grosse
06:25 – 06:30 Talk

Off-Policy Confidence Sequences
Publications connexes
- Off-Policy Confidence Sequences
  
  Nikos Karampatziakis, Paul Mineiro, Aaditya Ramdas
06:35 – 06:40 Talk

Quantum Algorithms for Reinforcement Learning with a Generative Model
Publications connexes
- Quantum algorithms for reinforcement learning with a generative model
  
  Daochen Wang, Aarthi Sundaram, Robin Kothari, Ashish Kapoor, Martin Roetteler
06:45 – 06:50 Talk

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
Publications connexes
- Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
  
  Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan (Jana) Kulkarni
07:00 – 07:20 Talk

Domain Generalization using Causal Matching
Publications connexes
- Domain Generalization using Causal Matching
  
  Divyat Mahajan, Shruti Tople, Amit Sharma
07:45 – 07:50 Talk

EL-Attention: Memory Efficient Lossless Attention for Generation
Publications connexes
- EL-Attention: Memory Efficient Lossless Attention for Generation
  
  Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan, Ruofei Zhang
08:00 – 09:00 Poster session

Poster Session 5
Publications connexes
- Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
  
  Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan (Jana) Kulkarni
- Differentially Private Correlation Clustering
  
  Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni
- Domain Generalization using Causal Matching
  
  Divyat Mahajan, Shruti Tople, Amit Sharma
- EL-Attention: Memory Efficient Lossless Attention for Generation
  
  Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan, Ruofei Zhang
- Memory-Efficient Pipeline-Parallel DNN Training
  
  Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, Xie Chen, Matei Zaharia
- Off-Policy Confidence Sequences
  
  Nikos Karampatziakis, Paul Mineiro, Aaditya Ramdas
- Quantum algorithms for reinforcement learning with a generative model
  
  Daochen Wang, Aarthi Sundaram, Robin Kothari, Ashish Kapoor, Martin Roetteler
- Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
  
  Shengyang Sun, Jiaxin Shi, Andrew Wilson, Roger Grosse
17:35 – 17:40 Talk

Statistical Estimation from Dependent Data
Publications connexes
- Statistical Estimation from Dependent Data
  
  Vardis Kandiros, Yuval Dagan, Nishanth Dikkala, Surbhi Goel, Constantinos Daskalakis
17:40 – 17:45 Talk

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
Publications connexes
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
  
  Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
17:40 – 17:45 Talk

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
Publications connexes
- Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
  
  Luisa Zintgraf, Leo Feng, Cong Lu, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, Shimon Whiteson
17:40 – 17:45 Talk

Decomposed Mutual Information Estimation for Contrastive Representation Learning
Publications connexes
- Decomposed Mutual Information Estimation for Contrastive Representation Learning
  
  Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Philip Bachman, Remi Tachet des Combes
17:45 – 17:50 Talk

Grey-box Extraction of Natural Language Models
Publications connexes
- Grey-box Extraction of Natural Language Models
  
  Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
18:00 – 18:20 Talk

WILDS: A Benchmark of in-the-Wild Distribution Shifts
Publications connexes
- WILDS: A Benchmark of in-the-Wild Distribution Shifts
  
  Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton Earnshaw, Imran Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang
18:20 – 18:25 Talk

Large Scale Private Learning via Low-rank Reparametrization
Publications connexes
- Large Scale Private Learning via Low-rank Reparametrization
  
  Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
18:35 – 18:40 Talk

Integrated Defense for Resilient Graph Matching
Publications connexes
- Integrated Defense for Resilient Graph Matching
  
  Jiaxiang Ren, Zijie Zhang, Jiayin Jin, Xin Zhao, Sixing Wu, Yang Zhou, Yelong Shen, Tianshi Che, Ruoming Jin, Dejing Dou, Yelong Shen
18:40 – 18:45 Talk

Differentially Private Correlation Clustering
Publications connexes
- Differentially Private Correlation Clustering
  
  Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni
19:00 – 19:20 Talk

Graph Neural Networks Inspired by Classical Iterative Algorithms
Publications connexes
- Graph Neural Networks Inspired by Classical Iterative Algorithms
  
  Yongyi Yang, Tang Liu, Yangkun Wang, Jinjing Zhou, Quan Gan, Zhewei Wei, Zheng Zhang, Zengfeng Huang, David Wipf
19:00 – 19:20 Talk

Correlation Clustering in Constant Many Parallel Rounds
Publications connexes
- Correlation Clustering in Constant Many Parallel Rounds
  
  Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
19:25 – 19:30 Talk

Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
Publications connexes
- Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
  
  Bohang Zhang, Tianle Cai, Zhou Lu, Di He, Liwei Wang
19:30 – 19:35 Talk

Finding k in Latent k-polytope
Publications connexes
- Finding k in Latent k-polytope
  
  Chiranjib Bhattacharyya, Ravi Kannan, Amit Kumar
19:35 – 19:40 Talk

On the Problem of Underranking in Group-Fair Ranking
Publications connexes
- On the Problem of Underranking in Group-Fair Ranking
  
  Sruthi Gorantla, Amit Deshpande, Anand Louis
20:00 – 21:00 Poster session

Poster Session 6
Publications connexes
- Correlation Clustering in Constant Many Parallel Rounds
  
  Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
- Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
  
  Luisa Zintgraf, Leo Feng, Cong Lu, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, Shimon Whiteson
- Finding k in Latent k-polytope
  
  Chiranjib Bhattacharyya, Ravi Kannan, Amit Kumar
- Graph Neural Networks Inspired by Classical Iterative Algorithms
  
  Yongyi Yang, Tang Liu, Yangkun Wang, Jinjing Zhou, Quan Gan, Zhewei Wei, Zheng Zhang, Zengfeng Huang, David Wipf
- Grey-box Extraction of Natural Language Models
  
  Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
- Integrated Defense for Resilient Graph Matching
  
  Jiaxiang Ren, Zijie Zhang, Jiayin Jin, Xin Zhao, Sixing Wu, Yang Zhou, Yelong Shen, Tianshi Che, Ruoming Jin, Dejing Dou, Yelong Shen
- Large Scale Private Learning via Low-rank Reparametrization
  
  Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
- On the Problem of Underranking in Group-Fair Ranking
  
  Sruthi Gorantla, Amit Deshpande, Anand Louis
- Online Learning with Optimism and Delay
  
  Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey
- Statistical Estimation from Dependent Data
  
  Vardis Kandiros, Yuval Dagan, Nishanth Dikkala, Surbhi Goel, Constantinos Daskalakis
- Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
  
  Bohang Zhang, Tianle Cai, Zhou Lu, Di He, Liwei Wang
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
  
  Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
- WILDS: A Benchmark of in-the-Wild Distribution Shifts
  
  Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton Earnshaw, Imran Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang
- Decomposed Mutual Information Estimation for Contrastive Representation Learning
  
  Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Philip Bachman, Remi Tachet des Combes
- BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
  
  Weizhen Qi, Yeyun Gong, Jian Jiao, Yu Yan, Dayiheng Liu, Wei Chen, Kewen Tang, Houqiang Li, Jiusheng Chen, Ruofei Zhang, Ming Zhou, Nan Duan
20:30 – 20:35 Talk

BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining

Weizhen Qi, Yeyun Gong, Jian Jiao, Yu Yan, Weizhu Chen, Dayiheng Liu, Kewen Tang, Houqiang Li, Jiu Jiusheng Chen, Ruofei Zhang, Ming Zhou, Nan Duan
Publications connexes
- BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
  
  Weizhen Qi, Yeyun Gong, Jian Jiao, Yu Yan, Dayiheng Liu, Wei Chen, Kewen Tang, Houqiang Li, Jiusheng Chen, Ruofei Zhang, Ming Zhou, Nan Duan
20:40 – 20:45 Talk

Online Learning with Optimism and Delay
Publications connexes
- Online Learning with Optimism and Delay
  
  Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey
20:50 – 20:55 Talk

Bayesian Structural Adaptation for Continual Learning
Publications connexes
- A Unified Bayesian Framework for Discriminative and Generative Continual Learning
  
  Abhishek Kumar, Sunabha Chatterjee, Piyush Rai

05:55 – 13:35 Workshop

Human-AI Collaboration in Sequential Decision-Making

Besmira Nushi, Adish Singla, Sebastian Tschiatschek
06:00 – 14:00 Workshop

Uncertainty and Robustness in Deep Learning

Balaji Lakshminarayanan, Dan Hendrycks, Sharon Li, Jasper Snoek, Silvia Chiappa, Sebastian Nowozin, Tom Dietterich
06:15 – 14:45 Workshop

Interpretable Machine Learning in Healthcare
Publications connexes
- Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs
  
  Shruthi Bannur, Ozan Oktay, Melanie Bernhardt, Anton Schwaighofer, Rajesh Jena, Besmira Nushi, Sharan Wadhwani, Aditya Nori, Kal Natarajan, Shazad Ashraf, Javier Alvarez-Valle, Daniel Coelho de Castro

06:20 – 14:00 Workshop

Workshop on Computational Approaches to Mental Health

Niranjani Prasad, Caroline Weis, Ida Momennejad, Rosanne Liu, Jake Vasilakes, Agni Kumar, Tianlin Zhang, Shems Saleh, Danielle Belgrave
08:45 – 18:05 Workshop

Time Series Workshop

Yian Ma, Ehi Nosakhare, Yuyang Wang, Scott Yang, Rose Yu

Microsoft at ICML 2021

Sunday, July 18, 2021

Real World RL: Azure Personalizer & Vowpal Wabbit

Cool Moves: Decoupling Physical Motions and Self-avatar Motions in Virtual Reality

Monday, July 19, 2021

Responsible AI in Industry: Practical Challenges and Lessons Learned

Social Implications of Large Language Models

Privacy in learning: Basics and the interplay

Tuesday, July 20, 2021

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation

Dataset Dynamics via Gradient Flows in Probability Space

Exploiting structured data for learning contagious diseases under incomplete testing

Evolving Attention with Residual Convolutions

Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference

Acceleration via Fractal Learning Rate Schedules

Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size

Interactive Learning from Activity Description

Poster Session 1

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Poolingformer: Long Document Modeling with Pooling Attention

Network Inference and Influence Maximization from Samples

Dueling Convex Optimization

Temporally Correlated Task Scheduling for Sequence Learning

Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed

Neural Pharmacodynamic State Space Modeling

Poster Session 2

Wednesday, July 21, 2021

Women in Machine Learning (WiML) Un-Workshop

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

How could Neural Networks understand Programs?

Joint Online Learning and Decision-making via Dual Mirror Descent

ChaCha for Online AutoML

Poster Session 3

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks

Confidence-Budget Matching for Sequential Budgeted Learning

Adversarial Dueling Bandits

TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL

Feature Learning in Infinite-Width Neural Networks

Interaction-Grounded Learning

Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics

Incentivizing Compliance with Algorithmic Instruments

Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning

Provably Correct Optimization and Exploration with Non-linear Policies

Safe Reinforcement Learning Using Advantage-Based Intervention

Poster Session 4

Thursday, July 22, 2021

Memory-Efficient Pipeline-Parallel DNN Training

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition

Off-Policy Confidence Sequences

Quantum Algorithms for Reinforcement Learning with a Generative Model

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Domain Generalization using Causal Matching

EL-Attention: Memory Efficient Lossless Attention for Generation

Poster Session 5

Statistical Estimation from Dependent Data

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Grey-box Extraction of Natural Language Models

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Large Scale Private Learning via Low-rank Reparametrization

Integrated Defense for Resilient Graph Matching

Differentially Private Correlation Clustering

Graph Neural Networks Inspired by Classical Iterative Algorithms

Correlation Clustering in Constant Many Parallel Rounds

Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons

Finding k in Latent k-polytope

On the Problem of Underranking in Group-Fair Ranking

Poster Session 6

BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining

Online Learning with Optimism and Delay

Bayesian Structural Adaptation for Continual Learning

Friday, July 23, 2021

Human-AI Collaboration in Sequential Decision-Making

Uncertainty and Robustness in Deep Learning

Interpretable Machine Learning in Healthcare

Saturday, July 24, 2021