Adaptive, Doubly Optimal No-Regret Learning Algorithms for Strongly Monotone Games and Exp-Concave Games with Gradient Feedback
The paper presents feasible variants of online gradient descent (AdaOGD) and online Newton step (AdaONS) that achieve optimal regret in the single-agent setting and optimal last-iterate convergence to the unique Nash equilibrium in the multi-agent setting, without requiring any prior knowledge of problem parameters.