← Search

John Lazarsfeld

2 accepted papers

2025

Optimism Without Regularization: Constant Regret in Zero-Sum Games

NeurIPS 2025poster

This paper studies the *optimistic* variant of Fictitious Play for learning in two-player zero-sum games. While it is known that Optimistic FTRL -- a *regularized* algorithm with a bounded stepsize parameter -- obtains constant regret in this setting, we show for the first time that similar, optima…

Cited by 0SourceScholar
2022

Differentially Private Maximal Information Coefficients

ICML 2022spotlight

The Maximal Information Coefficient (MIC) is a powerful statistic to identify dependencies between variables. However, it may be applied to sensitive data, and publishing it could leak private information. As a solution, we present algorithms to approximate MIC in a way that provides differential pr…