NO-REGRET ALGORITHMS IN ON-LINE LEARNING, GAMES AND CONVEX OPTIMIZATION

Sylvain Sorin (1)

1 IMJ-PRG (UMR_7586) - Institut de Mathématiques de Jussieu - Paris Rive Gauche

The purpose of this article is to underline the links between some no-regret algorithms used in on-line learning, games and convex optimization and to compare the continuous and discrete time versions.

Domaines: Optimisation et contrôle [math.OC]; Mathématiques [math]

Sylvain Sorin. NO-REGRET ALGORITHMS IN ON-LINE LEARNING, GAMES AND CONVEX OPTIMIZATION. 2022. ⟨hal-03911132⟩