Jeffrey Negrea (University of Waterloo)
Title:聽Follow-the-Perturbed-Leader with Between-Action Dependence.
Abstract:聽We present a framework for analyzing Gaussian follow-the-perturbed-leader (FTPL) algorithms for full-information online learning problems when the perturbation distribution exhibits between-action dependence. Applications include FTPL algorithms for online learning for i) infinite action spaces when the adversary plays bounded Lipschitz reward functions, where the perturbations are random functions sampled from a Gaussian process; and ii) linear polyhedral games, where the perturbation is a random linear function. We demonstrate how to tightly account for dependence between actions in the FTPL analysis and present an ansatz for the selection of the perturbation distribution based on a Bayesian perspective of FTPL as a variant of Thompson sampling.
Venue: UQAM Pavillon Pr茅sident-Kennedy, salle PK-5115, Montr茅al