Archives

EDP : Yassine Laguel (université Côte d’Azur) : High Probability and Risk-Averse Guarantees for Stochastic Saddle Point Problems

Bâtiment Fermat, salle 4205

Résumé : We investigate the stochastic accelerated primal-dual algorithm for strongly-convex-strongly-concave (SCSC) saddle point problems, common in distributionally robust learning, game theory, and fairness in machine learning. Our algorithm offers optimal complexity in several settings and we provide high probability