Statistical Seminar: Every Monday at 2:00 pm.
Time: 2:00 pm – 3:00 pm
Date: 15th September
Place: 3001

Vianney PERCHET (CREST) – Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback

 Abstract: 

In this talk, I will introduce the problem of learning in zero-sum game, and especially for the problem of “last-iterate” convergence, unlike the traditional literature that looks at the average convergence (we argue it makes more sense). The interesting property is that the optimal rate is T^{-1/4} which is quite unusual (and unexpected) in this literature.

Organizers:

Anna KORBA (CREST), Karim LOUNICI (CMAP) , Jaouad MOURTADA (CREST)

Sponsors:
CREST-CMAP