2 papers
math.OC2025
Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games
Fathima Zarin Faizal, Asuman Ozdaglar, Martin J. Wainwright
We study best-response type learning dynamics for zero-sum polymatrix games under two information settings. The two settings are distinguished by the type of information that each…
stat.ML2025
Wild refitting for black box prediction
Martin J. Wainwright
We describe and analyze a computionally efficient refitting procedure for computing high-probability upper bounds on the instance-wise mean-squared prediction error of penalized no…