Publications

Dexterous Robotic Grasping with Object-Centric Visual Affordances
P. Mandikal and K. Grauman
ICRA, 2021
SPECTRE: Defending against backdoor attacks using robust covariance estimation
Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh
arXiv, 2021
Robust and Differentially Private Mean Estimation
Xiyang Liu, Weihao Kong, Sham Kakade, Sewoong Oh
arXiv, 2021
VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency
R. Gao and K. Grauman
CVPR, 2021
A Spectral Analysis of Dot-product Kernels
Meyer Scetbon, Zaid Harchaoui
AISTATS, 2021
A Superquantile Approach for Federated Learning with Heterogeneous Devices
Y. Laguel, K. Pillutla, J. Malick, Z. Harchaoui
CISS, 2021
Improved Graph Clustering
Yudong Chen, Sujay Sanghavi, Huan Xu
arXiv, 2021
Something New Versus Tried and True: Ensuring 'Innovative' AI is 'Good' AI
Stephen C. Slota, Kenneth R. Fleischmann, Sherri Greenberg, Nitin Verma, Brenna Cummings, Lan Li, Chris Shenefiel
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, and Peter Stone
JMLR, 2020
End-to-End Learning for Retrospective Change-Point Estimation
Corinne Jones, Zaid Harchaoui
MLSP, 2020
Good Systems, Bad Data? Interpretations of AI Hype and Failures
Stephen C. Slota, Kenneth R. Fleischmann, Sherri Greenberg, Nitin Verma, Brenna Cummings, Lan Li, Chris Shenefiel
asis&t, 2020
Generalizing Curricula for Reinforcement Learning
Sanmit Narvekar and Peter Stone
ICML, 2020
First-order Optimization for Superquantile-based Supervised Learning
Yassine Laguel, Jérome Malick, Zaid Harchaoui
MLSP, 2020
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
Zihan Zhang, Xiangyang Ji, Simon S. Du
arXiv, 2020
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
Daniel S. Brown, Russell Coleman, Ravi Srinivasan, Scott Niekum
ICML, 2020
Learning Deep ReLU Networks is Fixed Parameter Tractable
Sitan Chen, Adam R. Klivans, Raghu Meka
arXiv, 2020
Learning to Improve Multi-Robot Hallway Navigation
Jin-Soo Park, Brian Tsang, Harel Yedidsion, Garrett Warnell, Daehyun Kyoung, and Peter Stone
CoRL, 2020
Entanglement is Necessary for Optimal Quantum Property Testing
Sebastien Bubeck, Sitan Chen, Jerry Li
arXiv, 2020