Soumita Hait

activity

20222026

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.LG2025

Comparator-Adaptive $Φ$ -Regret: Improved Bounds, Simpler Algorithms, and Applications to Games

Soumita Hait, Ping Li, Haipeng Luo +1

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

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…

Comparator-Adaptive Φ-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games

Alternating Regret for Online Convex Optimization

Comparator-Adaptive $Φ$ -Regret: Improved Bounds, Simpler Algorithms, and Applications to Games