English

An improved regret analysis for UCB-N and TS-N

Machine Learning 2023-05-09 v1

Abstract

In the setting of stochastic online learning with undirected feedback graphs, Lykouris et al. (2020) previously analyzed the pseudo-regret of the upper confidence bound-based algorithm UCB-N and the Thompson Sampling-based algorithm TS-N. In this note, we show how to improve their pseudo-regret analysis. Our improvement involves refining a key lemma of the previous analysis, allowing a log(T)\log(T) factor to be replaced by a factor log2(α)+3\log_2(\alpha) + 3 for α\alpha the independence number of the feedback graph.

Keywords

Cite

@article{arxiv.2305.04093,
  title  = {An improved regret analysis for UCB-N and TS-N},
  author = {Nishant A. Mehta},
  journal= {arXiv preprint arXiv:2305.04093},
  year   = {2023}
}

Comments

5 pages

R2 v1 2026-06-28T10:27:45.601Z