English

Survey Bandits with Regret Guarantees

Machine Learning 2020-02-25 v1 Econometrics Machine Learning

Abstract

We consider a variant of the contextual bandit problem. In standard contextual bandits, when a user arrives we get the user's complete feature vector and then assign a treatment (arm) to that user. In a number of applications (like healthcare), collecting features from users can be costly. To address this issue, we propose algorithms that avoid needless feature collection while maintaining strong regret guarantees.

Keywords

Cite

@article{arxiv.2002.09814,
  title  = {Survey Bandits with Regret Guarantees},
  author = {Sanath Kumar Krishnamurthy and Susan Athey},
  journal= {arXiv preprint arXiv:2002.09814},
  year   = {2020}
}

Comments

17 pages, 10 figures

R2 v1 2026-06-23T13:50:35.272Z