---
title: "Best-of-Both-Worlds FTRL for Linear Bandits: The Interplay of Information Acquisition, Corruption, and Geometry"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.01299v1"
permalink: "https://feed.astralor.com/items/itm_73df53655e7c33abb4288572"
published: "2026-10-31T21:58:28.000Z"
score: 53
channel: "finance"
tags: ["Best-of-Both-Worlds FTRL","Linear Bandits","The Interplay","Information Acquisition","Corruption","Geometry","BOBW"]
---

# Best-of-Both-Worlds FTRL for Linear Bandits: The Interplay of Information Acquisition, Corruption, and Geometry

## 速览

We study \textit{best-of-both-worlds} (BOBW) algorithms for linear bandits, which aim to simultaneously guarantee $\gO(\sqrt T)$ regret in the adversarial regime and $\gO(\log T)$ regret in the stochastic regime over $T…

## 关键点

- We study \textit{best-of-both-worlds} (BOBW) algorithms for linear bandits, which aim to simultaneously guarantee $\gO(\sqrt T)$ regret in the adversarial regime and $\gO(\log T)$ regret in the stochastic regime over $T…
- For finite action sets, we introduce \emph{information-acquisition follow-the-regularized-leader} (\IAFTRL{}), the first BOBW algorithm based purely on the follow-the-regularized-leader (FTRL) framework that attains an …
- This resolves the open problem posed in~\cite{LeeEtAl2021,KongZ023,ItoT23,ZhaoItoLi2025}.

## 全文

We study \textit{best-of-both-worlds} (BOBW) algorithms for linear bandits, which aim to simultaneously guarantee $\gO(\sqrt T)$ regret in the adversarial regime and $\gO(\log T)$ regret in the stochastic regime over $T$ rounds. For finite action sets, we introduce \emph{information-acquisition follow-the-regularized-leader} (\IAFTRL{}), the first BOBW algorithm based purely on the follow-the-regularized-leader (FTRL) framework that attains an $\gO(\cstar\log T)$-type regret in the stochastic regime, where $\cstar$ is the information-acquisition complexity that characterizes instance-dependent optimality in linear bandits, while retaining the $\gO(\sqrt{T})$ regret guarantee in the adversarial regime. This resolves the open problem posed in~\cite{LeeEtAl2021,KongZ023,ItoT23,ZhaoItoLi2025}.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_73df53655e7c33abb4288572