-
Monday, December 7
18:15–18:30 PT | Oral: COVID/Health/Bio Applications
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
Xin Liu, Josh Fromm, Shwetak Patel, Daniel McDuff
Poster Session: December 7
19:00–19:10 PT | Spotlight: Representation/Relational
On the Equivalence between Online and Private Learnability beyond Binary Classification
Young H Jung, Baekjin Kim, Ambuj Tewari
Poster Session: December 7
20:20–20:30 PT | Spotlight: Reinforcement Learning
Safe Reinforcement Learning via Curriculum Induction
Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal
Poster Session: December 7
21:00–23:00 PT | Poster Session 0
Adversarial Attacks on Deep Graph Matching
Zijie Zhang, Zeru Zhang, Yang Zhou, Yelong Shen, Ruoming Jin, Dejing Dou
Constrained episodic reinforcement learning in concave-convex and knapsack settings
Kianté Brantley, Miro Dudik, Thodoris Lykouris, Sobhan Miryoosefi, Max Simchowitz, Aleksandrs Slivkins, Wen Sun
Hierarchical Poset Decoding for Compositional Generalization in Language
Yinuo Guo, Zeqi Lin, Jian-Guang Lou, Dongmei Zhang
Information Theoretic Regret Bounds for Online Nonlinear Control
Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikuláš Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, Will Hamilton
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, Ming Zhou
MOReL: Model-Based Offline Reinforcement Learning
Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, Thorsten Joachims
MPNet: Masked and Permuted Pre-training for Language Understanding
Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
Xin Liu, Josh Fromm, Shwetak Patel, Daniel McDuff
Oral Session: December 7
On the Equivalence between Online and Private Learnability beyond Binary Classification
Young H Jung, Baekjin Kim, Ambuj Tewari
Spotlight Session: December 7
Parametric Instance Classification for Unsupervised Visual Feature learning
Yue Cao, Zhenda Xie, Bin Liu, Yutong Lin, Zheng Zhang, Han Hu
Provably Good Batch Reinforcement Learning Without Great Exploration
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill
Restoring Negative Information in Few-Shot Object Detection
Yukuan Yang, Fangyun Wei, Miaojing Shi, Guoqi Li
Safe Reinforcement Learning via Curriculum Induction
Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal
Spotlight Session: December 7
Sampling-Decomposable Generative Adversarial Recommender
Binbin Jin, Defu Lian, Zheng Liu, Qi Liu, Jianhui Ma, Xing Xie, Enhong Chen
Understanding Global Feature Contributions With Additive Importance Measures
Ian Covert, Scott Lundberg, Su-In Lee
-
Tuesday, December 8
06:30–06:45 PT | Oral: Reinforcement Learning
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun
Poster Session: December 8
07:00–07:10 PT | Spotlight: Social/Privacy
Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates
Wenhao Luo, Wen Sun, Ashish Kapoor
Poster Session: December 8
07:30–07:40 PT | Spotlight: Vision Applications
Learning Semantic-aware Normalization for Generative Adversarial Networks
Heliang Zheng, Jianlong Fu, Yanhong Zeng, Zheng-Jun Zha, Jiebo Luo
Poster Session: December 8
07:40–08:00 PT | Demonstration
MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
Mark Hamilton, Lei Zhang, Bill Freeman, Marina Rogers, Darius Bopp, Johnny Bui, Margaret Wang, Mindren Lu, Zhenbang Chen, Christopher Hoder
08:20–08:30 PT | Spotlight: Reinforcement Learning
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
Chi Jin, Sham Kakade, Akshay Krishnamurthy, Qinghua Liu
Poster Session: December 8
09:00–11:00 PT | Poster Session 1
CoinPress: Practical Private Mean and Covariance Estimation
Sourav Biswas, Yihe Dong, Gautam Kamath, Jonathan Ullman
Cross-validation Confidence Intervals for Test Error
Pierre Bayle, Alexandre Bayle, Lucas Janson, Lester Mackey
Deep Reinforcement and InfoMax Learning
Bogdan Mazoure, Remi Tachet des Combes, Thang Long DOAN, Philip Bachman, R Devon Hjelm
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
Hadi Salman, Mingjie Sun, Greg Yang, Ashish Kapoor, J. Zico Kolter
Efficient Contextual Bandits with Continuous Actions
Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun
Oral Session: December 8
Learning Semantic-aware Normalization for Generative Adversarial Networks
Heliang Zheng, Jianlong Fu, Yanhong Zeng, Zheng-Jun Zha, Jiebo Luo
Spotlight Session: December 8
Learning Structured Distributions From Untrusted Batches: Faster and Simpler
Sitan Chen, Jerry Li, Ankur Moitra
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan Foster, Max Simchowitz, Wen Sun, Dipendra Misra, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates
Wenhao Luo, Wen Sun, Ashish Kapoor
Spotlight Session: December 8
Network size and size of the weights in memorization with two-layers neural networks
Sebastien Bubeck, Ronen Eldan, Yin Tat Lee, Dan Mikulincer
On Infinite-Width Hypernetworks
Etai Littwin, Tomer Galanti, Lior Wolf, Greg Yang
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Alekh Agarwal, Mikael Henaff, Sham Kakade, Wen Sun
Provably adaptive reinforcement learning in metric spaces
Tongyi Cao, Akshay Krishnamurthy
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
Bita Darvish Rouhani, Daniel Lo, Ritchie Zhao, Ming Liu, Jeremy Fowers, Kalin Ovtcharov, Anna Vinogradsky, Sarah Massengill, Lita Yang, Ray Bittner, Alessandro Forin, Haishan Zhu, Taesik Na, Prerak Patel, Shuai Che, Lok Chand Koppaka, Steve Reinhardt, Sitaram Lanka, Xia Song, Subhojit Som, Kaustav Das, Saurabh K T, Eric Chung, Doug Burger
RepPoints v2: Verification Meets Regression for Object Detection
Yihong Chen, Zheng Zhang, Yue Cao, Liwei Wang, Stephen Lin, Han Hu
Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
Sam Hopkins, Jerry Li, Fred Zhang
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
Chi Jin, Sham Kakade, Akshay Krishnamurthy, Qinghua Liu
Spotlight Session: December 8
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
Harm Van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar
18:30–18:45 PT | Oral: Vision Applications
Do Adversarially Robust ImageNet Models Transfer Better?
Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Madry
Poster Session: December 8
19:30–19:40 PT | Spotlight: Vision Applications
Large-Scale Adversarial Training for Vision-and-Language Representation Learning
Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, Jingjing Liu
Poster Session: December 8
19:50–20:00 PT | Spotlight: Deep Learning/Theory
Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing
Arun Jambulapati, Jerry Li, Kevin Tian
Poster Session: December 8
20:50–20:00 PT | Spotlight: Reinforcement Learning
Policy Improvement via Imitation of Multiple Oracles
Ching-An Cheng, Andrey Kolobov, Alekh Agarwal
Poster Session: December 8
21:00–23:00 PT | Poster Session 2
Do Adversarially Robust ImageNet Models Transfer Better?
Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Madry
Oral Session: December 8
GreedyFool: Distortion-Aware Sparse Adversarial Attack
Xiaoyi Dong, Dongdong Chen, Jianmin Bao, Chuan Qin, Lu Yuan, Weiming Zhang, Nenghai Yu, Dong Chen
Large-Scale Adversarial Training for Vision-and-Language Representation Learning
Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, Jingjing Liu
Spotlight Session: December 8
Policy Improvement via Imitation of Multiple Oracles
Ching-An Cheng, Andrey Kolobov, Alekh Agarwal
Spotlight Session: December 8
RD2: Reward Decomposition with Representation Disentanglement
Zichuan Lin, Derek Yang, Li Zhao, Tao Qin, Guangwen Yang, Tie-Yan Liu
Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time
Jerry Li, Guanghao Ye
Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing
Arun Jambulapati, Jerry Li, Kevin Tian
Spotlight Session: December 8
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
Wangchunshu Zhou, Jinyi Hu, Hanlin Zhang, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang
-
Wednesday, December 9
06:15–06:30 PT | Oral: COVID/Applications/Composition
Learning Composable Energy Surrogates for PDE Order Reduction
Alex Beatson, Jordan Ash, Geoffrey Roeder, Tianju Xue, Ryan Adams
Poster Session: December 9
07:00–07:10 PT | Spotlight: COVID/Applications/Composition
Compositional Generalization by Learning Analytical Expressions
Qian Liu, Shengnan An, Jian-Guang Lou, Bei Chen, Zeqi Lin, Yan Gao, Bin Zhou, Nanning Zheng, Dongmei Zhang
Poster Session: December 9
07:30–07:40 PT | Spotlight: Continual/Meta/Misc Learning
Uncertainty-aware Self-training for Few-shot Text Classification
Subhabrata Mukherjee, Ahmed Awadallah
Poster Session: December 9
07:50–08:00 PT | Spotlight: Deep Learning
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
Edward Moroshko, Suriya Gunasekar, Blake Woodworth, Jason Lee, Nati Srebro, Daniel Soudry
Poster Session: December 9
08:10–08:20 PT | Spotlight: Optimization
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms
Dheeraj Nagaraj, Xian Wu, Guy Bresler, Prateek Jain, Praneeth Netrapalli
Poster Session: December 9
09:00–11:00 PT | Poster Session 3
A Causal View on Robustness of Neural Networks
Cheng Zhang, Kun Zhang, Yingzhen Li
AvE: Assistance via Empowerment
Yuqing Du, Stas Tiomkin, Emre Kiciman, Daniel Polani, Pieter Abbeel, Anca Dragan
BERT Loses Patience: Fast and Robust Inference with Early Exit
Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, Furu Wei
Compositional Generalization by Learning Analytical Expressions
Qian Liu, Shengnan An, Jian-Guang Lou, Bei Chen, Zeqi Lin, Yan Gao, Bin Zhou, Nanning Zheng, Dongmei Zhang
Spotlight Session: December 9
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoffrey Gordon
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil Devanur, Divya Mahajan, Fanny Nina Paravecino
Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games
Arun Suggala, Praneeth Netrapalli
Geometric Dataset Distances via Optimal Transport
David Alvarez Melis, Nicolo Fusi
How do fair decisions fare in long-term qualification?
Xueru Zhang, Ruibo Tu, Yang Liu, mingyan liu, Hedvig Kjellstrom, Kun Zhang, Cheng Zhang
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
Edward Moroshko, Suriya Gunasekar, Blake Woodworth, Jason Lee, Nati Srebro, Daniel Soudry
Spotlight Session: December 9
Learning Composable Energy Surrogates for PDE Order Reduction
Alex Beatson, Jordan Ash, Geoffrey Roeder, Tianju Xue, Ryan Adams
Oral Session: December 9
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms
Dheeraj Nagaraj, Xian Wu, Guy Bresler, Prateek Jain, Praneeth Netrapalli
Spotlight Session: December 9
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
Zhining Liu, Pengfei Wei, Jing Jiang, Wei Cao, Jiang Bian, Yi Chang
Minimax Estimation of Conditional Moment Models
Nishanth Dikkala, Greg Lewis, Lester Mackey, Vasilis Syrgkanis
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
Chen Liu, Mathieu Salzmann, Tao LIN, Ryota Tomioka, Sabine Süsstrunk
Statistical Optimal Transport posed as Learning Kernel Embedding
Saketha Nath Jagarlapudi, Pratik Kumar Jawanpuria
The Pitfalls of Simplicity Bias in Neural Networks
Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, Praneeth Netrapalli
Uncertainty-aware Self-training for Few-shot Text Classification
Subhabrata Mukherjee, Ahmed Awadallah
Spotlight Session: December 9
Zero-Resource Knowledge-Grounded Dialogue Generation
Linxiao Li, Can Xu, Wei Wu, Yufan Zhao, Xueliang Zhao, Chongyang Tao
19:10–19:20 PT | Spotlight: Graph/Meta Learning/Software
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
Defu Cao, Yujing Wang, Juanyong Duan, Ce Zhang, Xia Zhu, Congrui Huang, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang
Poster Session: December 9
20:10–20:20 PT | Spotlight: Graph/Meta Learning/Software
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
Oindrila Saha, Venkata Aditya Kusupati, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain
Poster Session: December 9
20:20–20:30 PT | Spotlight: Vision Applications
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Cheng Chi, Fangyun Wei, Han Hu
Poster Session: December 9
21:00–23:00 PT | Poster Session 4
A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices
Jiezhong Qiu, Chi Wang, Ben Liao, Richard Peng, Jie Tang
Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment
Govinda Kamath, Tavor Baharav, Ilan Shomorony
GAN Memory with No Forgetting
Chunyuan Li, Miaoyun Zhao, Jianqiao Li, Sijia Wang, Lawrence Carin
Online Influence Maximization under Linear Threshold Model
Shuai Li, Fang Kong, Kejie Tang, Qizhi Li, Wei Chen
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Cheng Chi, Fangyun Wei, Han Hu
Spotlight Session: December 9
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
Oindrila Saha, Venkata Aditya Kusupati, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain
Spotlight Session: December 9
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
Defu Cao, Yujing Wang, Juanyong Duan, Ce Zhang, Xia Zhu, Congrui Huang, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang
Spotlight Session: December 9
-
Thursday, December 10
07:10–07:20 PT | Spotlight: Optimization
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Poster Session: December 10
08:20–08:30 PT | Spotlight: Graph/Relational/Theory
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples
Shafi Goldwasser, Adam Tauman Kalai, Yael Kalai, Omar Montasser
Poster Session: December 10
09:00–11:00 PT | Poster Session 5
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples
Shafi Goldwasser, Adam Tauman Kalai, Yael Kalai, Omar Montasser
Spotlight Session: December 10
COPT: Coordinated Optimal Transport on Graphs
Yihe Dong, Will Sawin
Empirical Likelihood for Contextual Bandits
Paul Mineiro, Nikos Karampatziakis, John Langford
Implicit Regularization and Convergence for Weight Normalization
Xiaoxia Wu, Edgar Dobriban, Tongzheng Ren, Shanshan Wu, Zhiyuan Li, Suriya Gunasekar, Rachel Ward, Qiang Liu
On the Expressiveness of Approximate Inference in Bayesian Neural Networks
Andrew Foong, David Burt, Yingzhen Li, Richard E Turner
On Warm-Starting Neural Network Training
Jordan Ash, Ryan Adams
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
Chao Ma, Sebastian Tschiatschek, Richard E Turner, José Miguel Hernández-Lobato, Cheng Zhang
18:30–18:45 PT | Oral: Optimization
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
Poster Session: December 10
21:00–23:00 PT | Poster Session 6
Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping
AdaTune: Adaptive Tensor Program Compilation Made Efficient
Menghao Li, Minjia Zhang, Chi Wang, Mingqin Li
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
Houwen Peng, Hao Du, Hongyuan Yu, QI LI, Jing Liao, Jianlong Fu
Disentangling Human Error from Ground Truth in Segmentation of Medical Images
Le Zhang, Ryutaro Tanno, Moucheng Xu, Chen Jin, Joseph Jacob, Olga Cicarrelli, Frederik Barkhof, Daniel Alexander
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
Oral Session: December 10
Graph Policy Network for Transferable Active Learning on Graphs
Shengding Hu, Zheng Xiong, Meng Qu, Xingdi Yuan, Marc-Alexandre Côté, Zhiyuan Liu, Jian Tang
HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory
Jie Ren, Minjia Zhang, Dong Li
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
Gellert Weisz, András György, Wei-I Lin, Devon Graham, Kevin Leyton-Brown, Csaba Szepesvari, Brendan Lucier
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
Amir Rahimi, Amirreza Shaban, Ching-An Cheng, Richard I Hartley, Byron Boots
Passport-aware Normalization for Deep Model Protection
Jie Zhang, Dongdong Chen, Jing Liao, Weiming Zhang, Gang Hua, Nenghai Yu
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Spotlight Session: December 10
Semi-Supervised Neural Architecture Search
Renqian Luo, Xu Tan, Rui Wang, Tao Qin, Enhong Chen, Tie-Yan Liu
Stochastic Stein Discrepancies
Jackson Gorham, Anant Raj, Lester Mackey