Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe
Machine Learning
2017-09-07 v2 Optimization and Control
Machine Learning
Abstract
We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily a cumulative loss. This framework allows us to study a very general class of problems, with applications in statistics, machine learning, and other fields. To solve this problem, we analyze the Upper-Confidence Frank-Wolfe algorithm, inspired by techniques for bandits and convex optimization. We give theoretical guarantees for the performance of this algorithm over various classes of functions, and discuss the optimality of these results.
Cite
@article{arxiv.1702.06917,
title = {Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe},
author = {Quentin Berthet and Vianney Perchet},
journal= {arXiv preprint arXiv:1702.06917},
year = {2017}
}