Nearly dimension-independent sparse linear bandit over small action spaces via best subset selection

Yining Wang, Yi Chen, Ethan X. Fang, Zhaoran Wang, Runze Li

Research output: Contribution to journalArticlepeer-review

Abstract

We consider the stochastic contextual bandit problem under the high dimensional linear model. We focus on the case where the action space is finite and random, with each action associated with a randomly generated contextual covariate. This setting finds essential applications such as personalized recommendation, online advertisement, and personalized medicine. However, it is very challenging as we need to balance exploration and exploitation. We propose doubly growing epochs and estimating the parameter using the best subset selection method, which is easy to implement in practice. This approach achieves Orps?Tq regret with high probability, which is nearly independent in the “ambient” regression model dimension d. We further attain a sharper Orp?sTq regret by using the SUPLINUCB framework and match the minimax lower bound of low-dimensional linear stochastic bandit problems. Finally, we conduct extensive numerical experiments to demonstrate the applicability and robustness of our algorithms empirically.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Sep 4 2020

Keywords

  • Best subset selection
  • High-dimensional models
  • Regret analysis
  • Stochastic bandit

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Nearly dimension-independent sparse linear bandit over small action spaces via best subset selection'. Together they form a unique fingerprint.

Cite this