When both players play strongly convex losses, an extragradient method attains duality gap with high probability.
Paper COLT 2025 Bandits and online learning
Logarithmic Regret for Convex–Concave Saddle Problems
Cite this paper
Logarithmic Regret for Convex–Concave Saddle Problems
@inproceedings{singh2025log,
title = {Logarithmic Regret for Convex–Concave Saddle Problems},
author = {Maya Singh and Renat Ostrovsky and Leila Aydın},
booktitle = {COLT 2025},
year = {2025}
}