May 17, 2018 · Abstract:We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games.

Abstract. We consider the use of no-regret algorithms to compute equilibria for particular classes of convex- concave games. While standard regret bounds ...

It is shown that for a particular class of games one achieves a $O(1/T^2)$ rate, and it is shown how this applies to the Frank-Wolfe method and recovers a ...

May 17, 2018 · Abstract. We consider the use of no-regret algorithms to compute equilibria for particular classes of convex- concave games.

Mathematics · Regret 100% · Game 64% · Class 23% · Convergence Rate 22% · Prediction 21% · Curvature 20% · Standards 14%.

Fingerprint. Dive into the research topics of 'Faster Rates for Convex-Concave Games'. Together they form a unique fingerprint.

Missing: Faster Rates

Oct 31, 2022 · The paper studies simultaneous no-regret learning in a subset of convex games (satisfying a variational stability condition) when players ...

This paper shows that Nesterov's accelerated gradient descent algorithms can be interpreted as computing a saddle point via online optimization algorithms.

We investigate three kinds of time- varying strongly monotone games, including distributed l2-regularized logistic regression, Cournot competition, and strongly ...