Saved in:
Bibliographic Details
Main Authors: Brukhim, Nataly, Cesa-Bianchi, Nicolò, Ciliberto, Carlo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.00803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908858663829504
author Brukhim, Nataly
Cesa-Bianchi, Nicolò
Ciliberto, Carlo
author_facet Brukhim, Nataly
Cesa-Bianchi, Nicolò
Ciliberto, Carlo
contents We study an identification problem in multi-armed bandits. In each round a learner selects one of $K$ arms and observes its reward, with the goal of eventually identifying an arm that will perform best at a {\it future} time. In adversarial environments, however, past performance may offer little information about the future, raising the question of whether meaningful identification is possible at all. In this work, we introduce \emph{lookahead identification}, a task in which the goal of the learner is to select a future prediction window and commit in advance to an arm whose average reward over that window is within $\varepsilon$ of optimal. Our analysis characterizes both the achievable accuracy of lookahead identification and the memory resources required to obtain it. From an accuracy standpoint, for any horizon $T$ we give an algorithm achieving $\varepsilon = O\bigl(1/\sqrt{\log T}\bigr)$ over $Ω(\sqrt{T})$ prediction windows. This demonstrates that, perhaps surprisingly, identification is possible in adversarial settings, despite significant lack of information. We also prove a near-matching lower bound showing that $\varepsilon = Ω\bigl(1/\log T\bigr)$ is unavoidable. We then turn to investigate the role of memory in our problem, first proving that any algorithm achieving nontrivial accuracy requires $Ω(K)$ bits of memory. Under a natural \emph{local sparsity} condition, we show that the same accuracy guarantees can be achieved using only poly-logarithmic memory.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00803
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Lookahead identification in adversarial bandits: accuracy and memory bounds
Brukhim, Nataly
Cesa-Bianchi, Nicolò
Ciliberto, Carlo
Machine Learning
We study an identification problem in multi-armed bandits. In each round a learner selects one of $K$ arms and observes its reward, with the goal of eventually identifying an arm that will perform best at a {\it future} time. In adversarial environments, however, past performance may offer little information about the future, raising the question of whether meaningful identification is possible at all. In this work, we introduce \emph{lookahead identification}, a task in which the goal of the learner is to select a future prediction window and commit in advance to an arm whose average reward over that window is within $\varepsilon$ of optimal. Our analysis characterizes both the achievable accuracy of lookahead identification and the memory resources required to obtain it. From an accuracy standpoint, for any horizon $T$ we give an algorithm achieving $\varepsilon = O\bigl(1/\sqrt{\log T}\bigr)$ over $Ω(\sqrt{T})$ prediction windows. This demonstrates that, perhaps surprisingly, identification is possible in adversarial settings, despite significant lack of information. We also prove a near-matching lower bound showing that $\varepsilon = Ω\bigl(1/\log T\bigr)$ is unavoidable. We then turn to investigate the role of memory in our problem, first proving that any algorithm achieving nontrivial accuracy requires $Ω(K)$ bits of memory. Under a natural \emph{local sparsity} condition, we show that the same accuracy guarantees can be achieved using only poly-logarithmic memory.
title Lookahead identification in adversarial bandits: accuracy and memory bounds
topic Machine Learning
url https://arxiv.org/abs/2603.00803