DeLTA seminar by Julian Zimmert

Speaker

Julian Zimmert, Google Research

Title

A Blackbox Approach to Best of Both Worlds in Bandits and Beyond

Abstract

Best-of-both-worlds algorithms for online learning which achieve near-optimal regret in both the adversarial and the stochastic regimes have received significant attention in the recent past. Existing techniques require careful adaptation to every new problem setup, including specialised potentials and careful tuning of algorithm parameters. In this work, we present a general reduction that allows us to obtain best-of-both-worlds guarantees for a wide family of follow-the-regularized-leader (FTRL) algorithms. We showcase the capability of this reduction by transforming existing algorithms, only known to achieve worst-case guarantees, into new algorithms with best-of-both-worlds guarantees in contextual bandits, graph bandits and tabular Markov decision processes.