Ping Li

collaborators

3 papers

cs.LG2026

Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions

Soumita Hait, Ping Li, Haipeng Luo +1

Last-iterate convergence of learning dynamics in games has attracted significant recent attention. In two-player zero-sum games with bandit feedback, where only the loss of the sel…

cs.LG2025

Comparator-Adaptive $I^¦$ -Regret: Improved Bounds, Simpler Algorithms, and Applications to Games

Soumita Hait, Ping Li, Haipeng Luo +1

In the classic expert problem, $I^¦$ -regret measures the gap between the learner's total loss and that achieved by applying the best action transformation $I ¨ \in I^¦$ . A recent work…

cs.LG2025

Alternating Regret for Online Convex Optimization

Soumita Hait, Ping Li, Haipeng Luo +1

Motivated by alternating learning dynamics in two-player games, a recent work by Cevher et al.(2024) shows that $o (T)$ alternating regret is possible for any $T$ -round adver…

Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions

Comparator-Adaptive I^¦-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games

Alternating Regret for Online Convex Optimization

Comparator-Adaptive $I^¦$ -Regret: Improved Bounds, Simpler Algorithms, and Applications to Games