–
Coffee and Check In
–
Opening Remarks
–
Constant Regret in Exchangeable Action Models: Overbooking, Bin Packing, and Beyond
Daniel Freund (MIT)
–
Coffee Break
–
Stochastic Bin Packing with Time-Varying Item Sizes
Weina Wang (Carnegie Mellon University)
–
Lunch
–
A Tutorial on Finite-Sample Guarantees of Contractive Stochastic Approximation With Applications in Reinforcement Learning
Siva Theja Maguluri (Georgia Institute of Technology)
–
Coffee Break
–
A Tutorial on Finite-Sample Guarantees of Contractive Stochastic Approximation With Applications in Reinforcement Learning
Zaiwei Chen (Caltech)
–
Reception (In conjunction with the Peter Bartlett recognition event)
–
Coffee and Check In
–
The Statistical Complexity of Interactive Decision Making
Dylan Foster (Microsoft Research)
–
Break
–
A Game-Theoretic Approach to Offline Reinforcement Learning
Ching-An Cheng (Microsoft Research)
–
Lunch
–
Are Multicriteria MDPs Harder to Solve Than Single-Criteria MDPs?
Csaba Szepasvari (University of Alberta, Google DeepMind)
–
Break
–
Learning Across Bandits in High Dimension via Robust Statistics
Hamsa Bastani (University of Pennsylvania)
–
Coffee and Check In
–
Fast Algorithms for Online Stochastic Convex Programming
Nikhil Devanur (Amazon)
–
Break
–
New Results on Primal-Dual Algorithms for Online Allocation Problems With Applications to Budget Pacing in Online Advertising
Haihao Lu (Chicago Booth School of Business)
–
Lunch
–
Dynamic Spatial Matching and Applications
Yash Kanoria (Columbia University)
–
Break
–
Poster Session (In-Person Only)
–
Coffee and Check In
–
Optimal Learning for Structured Bandits
Negin Golrezei (Massachusetts Institute of Technology)
–
Break
–
When Matching Meets Batching: Optimal Multi-stage Algorithms and Applications
Rad Niazadeh (The University of Chicago Booth School of Business)
–
Lunch
–
The Power of Adaptivity in Representation Learning: From Meta-Learning to Federated Learning
Sanjay Shakkottai (University of Texas at Austin)
–
Break
–
Open Problem Session (In-Person Only)
–
Coffee and Check In
–
Near-Optimal No-Regret Learning for General Convex Games
Gabriele Farina (Carnegie Mellon University)
–
Break
–
Learning to Control Safety-Critical Systems
Adam Wierman (California Institute of Technology)