Workshops

Spring 2022

Adversarial Approaches in Machine Learning

Feb 22, 2022 to Feb 25, 2022

Return to event »

All talks are in Pacific Time.

Tuesday, February 22nd, 2022
8:30 am–8:55 am		Coffee and Check-In
8:55 am–9:00 am		Opening Remarks
9:00 am–9:45 am		Last-Iterate Convergence in Constrained Min-Max Optimization: SOS to the Rescue Yang Cai (Yale University)
9:45 am–10:15 am		Break
10:15 am–11:00 am		Optimistic Gradient Methods for Multi-Agent Learning Kaiqing Zhang (MIT)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Fast Rates for No-Regret Learning in General Games Noah Golowich (MIT)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:45 pm		Offline Reinforcement Learning With Only Realizability Jason Lee (Princeton)
2:45 pm–3:15 pm		Break
3:15 pm–4:00 pm		The Variational Method of Moments Nathan Kallus (Cornell University)
4:00 pm–5:00 pm		Reception

Wednesday, February 23rd, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Min-max Optimization: From Complexity to Algorithms Emmanouil Zampetakis (UC Berkeley)
9:45 am–10:15 am		Break
10:15 am–11:00 am		Min-Max Optimization from a Dynamical Systems Viewpoint Panayotis Mertikopoulos (CNRS)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Smooth Nonconvex Min-Max Optimization Meisam Razaviyayn (University of Southern California)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:45 pm		Studying Failure Modes of Deep Learning and Ways To Fix Them Soheil Feizi (University of Maryland, College Park)
2:45 pm–3:15 pm		Break
3:15 pm–4:00 pm		Is Minimax Optimization the Right Framework to Understand Learning in Minimax Games? Gauthier Gidel (Université de Montréal)
4:00 pm–4:15 pm		Break
4:15 pm–5:00 pm		Beyond Adversarial Approaches on Distributional Robustness Qi Lei (Princeton)

Thursday, February 24th, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Computationally Efficient Alternatives to Nonconvex-Nonconcave Min-Max Optimization Nisheeth Vishnoi (Yale University)
9:45 am–10:15 am		Break
10:15 am–11:00 am		Halpern Iteration and Equilibria Problems Jelena Diakonikolas (University of Wisconsin-Madison)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Zeroth-Order Methods for Convex-Concave Minmax Problems: Learning from Strategically Generated Data Chinmay Maheshwari (UC Berkeley)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:45 pm		Are Single-Loop Algorithms Sufficient for Unbalanced Minimax Optimization？ Niao He (ETH Zürich)
2:45 pm–3:15 pm		Break
3:15 pm–4:00 pm		Policy Gradient: Optimal Estimation, Convergence, and Generalization beyond Cumulative Rewards Mengdi Wang (Princeton University)
4:00 pm–4:15 pm		Break
4:15 pm–5:00 pm		Of Moments and Matching: Trade-offs and Treatments in Imitation Learning Steven Wu (Carnegie Mellon University)

Friday, February 25th, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Learning Uninformative Representations Richard Zemel (Columbia University)
9:45 am–10:15 am		Break
10:15 am–11:00 am		Generalized Energy-Based Models Arthur Gretton (UCL)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Rebel: Combining Deep Reinforcement Learning and Search for Imperfect-Information Games Noam Brown (Facebook AI Research)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:45 pm		Online Adversarial Multicalibration And (Multi)Calibeating Aaron Roth (University of Pennsylvania)
2:45 pm–3:15 pm		Break
3:15 pm–4:00 pm		Adversarial Machine Learning and Instrumental Variables for Flexible Causal Modeling Vasilis Syrgkanis (Microsoft Research)