English

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.

Keywords

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}
}
R2 v1 2026-06-22T18:25:36.979Z