LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kato, Masahiro, Ito, Shinji
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913862575456256
author Kato, Masahiro
Ito, Shinji
author_facet Kato, Masahiro
Ito, Shinji
contents We investigate the \emph{linear contextual bandit problem} with independent and identically distributed (i.i.d.) contexts. In this problem, we aim to develop a \emph{Best-of-Both-Worlds} (BoBW) algorithm with regret upper bounds in both stochastic and adversarial regimes. We develop an algorithm based on \emph{Follow-The-Regularized-Leader} (FTRL) with Tsallis entropy, referred to as the $α$-\emph{Linear-Contextual (LC)-Tsallis-INF}. We show that its regret is at most $O(\log(T))$ in the stochastic regime under the assumption that the suboptimality gap is uniformly bounded from below, and at most $O(\sqrt{T})$ in the adversarial regime. Furthermore, our regret analysis is extended to more general regimes characterized by the \emph{margin condition} with a parameter $β\in (1, \infty]$, which imposes a milder assumption on the suboptimality gap. We show that the proposed algorithm achieves $O\left(\log(T)^{\frac{1+β}{2+β}}T^{\frac{1}{2+β}}\right)$ regret under the margin condition.
format Preprint
id arxiv_https___arxiv_org_abs_2403_03219
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
Kato, Masahiro
Ito, Shinji
Machine Learning
We investigate the \emph{linear contextual bandit problem} with independent and identically distributed (i.i.d.) contexts. In this problem, we aim to develop a \emph{Best-of-Both-Worlds} (BoBW) algorithm with regret upper bounds in both stochastic and adversarial regimes. We develop an algorithm based on \emph{Follow-The-Regularized-Leader} (FTRL) with Tsallis entropy, referred to as the $α$-\emph{Linear-Contextual (LC)-Tsallis-INF}. We show that its regret is at most $O(\log(T))$ in the stochastic regime under the assumption that the suboptimality gap is uniformly bounded from below, and at most $O(\sqrt{T})$ in the adversarial regime. Furthermore, our regret analysis is extended to more general regimes characterized by the \emph{margin condition} with a parameter $β\in (1, \infty]$, which imposes a milder assumption on the suboptimality gap. We show that the proposed algorithm achieves $O\left(\log(T)^{\frac{1+β}{2+β}}T^{\frac{1}{2+β}}\right)$ regret under the margin condition.
title LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
topic Machine Learning
url https://arxiv.org/abs/2403.03219