English

Stochastic Linear Contextual Bandits with Diverse Contexts

Machine Learning 2020-03-06 v1 Information Theory math.IT Machine Learning

Abstract

In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently diverse, the learner is able to utilize the information obtained during exploitation to shorten the exploration process, thus achieving reduced regret. We design the LinUCB-d algorithm, and propose a novel approach to analyze its regret performance. The main theoretical result is that under the diverse context assumption, the cumulative expected regret of LinUCB-d is bounded by a constant. As a by-product, our results improve the previous understanding of LinUCB and strengthen its performance guarantee.

Keywords

Cite

@article{arxiv.2003.02681,
  title  = {Stochastic Linear Contextual Bandits with Diverse Contexts},
  author = {Weiqiang Wu and Jing Yang and Cong Shen},
  journal= {arXiv preprint arXiv:2003.02681},
  year   = {2020}
}

Comments

Accepted to AISTATS 2020

R2 v1 2026-06-23T14:05:11.060Z