English

MNL-Bandit in non-stationary environments

Machine Learning 2023-06-05 v2 Artificial Intelligence Machine Learning

Abstract

In this paper, we study the MNL-Bandit problem in a non-stationary environment and present an algorithm with a worst-case expected regret of O~(min{NTL  ,  N13(ΔK)13T23+NT})\tilde{O}\left( \min \left\{ \sqrt{NTL}\;,\; N^{\frac{1}{3}}(\Delta_{\infty}^{K})^{\frac{1}{3}} T^{\frac{2}{3}} + \sqrt{NT}\right\}\right). Here NN is the number of arms, LL is the number of changes and ΔK\Delta_{\infty}^{K} is a variation measure of the unknown parameters. Furthermore, we show matching lower bounds on the expected regret (up to logarithmic factors), implying that our algorithm is optimal. Our approach builds upon the epoch-based algorithm for stationary MNL-Bandit in Agrawal et al. 2016. However, non-stationarity poses several challenges and we introduce new techniques and ideas to address these. In particular, we give a tight characterization for the bias introduced in the estimators due to non stationarity and derive new concentration bounds.

Keywords

Cite

@article{arxiv.2303.02504,
  title  = {MNL-Bandit in non-stationary environments},
  author = {Ayoub Foussoul and Vineet Goyal and Varun Gupta},
  journal= {arXiv preprint arXiv:2303.02504},
  year   = {2023}
}