Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pasteris, Stephen, Savani, Rahul, Turocy, Theodore
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.05266
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914536244641792
author Pasteris, Stephen
Savani, Rahul
Turocy, Theodore
author_facet Pasteris, Stephen
Savani, Rahul
Turocy, Theodore
contents We consider the extensive-form bandit problem, where on each trial the learner (a user coordinated by a server) plays an extensive-form game against an oblivious adversary, observing the information sets it finds itself in as well as the resulting payoff/loss. We give an algorithm for this problem that satisfies $ε$-local differential privacy and attains a regret of $\tilde{O}(\sqrt{A\ln(S)T}/ε)$, where $A$ is the total number of actions that the learner can possibly take, $S$ is the number of the learner's possible reduced strategies, and $T$ is the number of trials. On each trial, the time complexity of our algorithm is, up to a factor logarithmic in the maximum number of actions at an infoset, equal to the time required for the server to transmit the reduced strategy to the user. We note that local differential privacy is the strongest version of differential privacy and, to the best of our knowledge, this is the first work to study differential privacy of any form in the extensive-form bandit problem.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05266
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differential Privacy in the Extensive-Form Bandit Problem
Pasteris, Stephen
Savani, Rahul
Turocy, Theodore
Cryptography and Security
Machine Learning
We consider the extensive-form bandit problem, where on each trial the learner (a user coordinated by a server) plays an extensive-form game against an oblivious adversary, observing the information sets it finds itself in as well as the resulting payoff/loss. We give an algorithm for this problem that satisfies $ε$-local differential privacy and attains a regret of $\tilde{O}(\sqrt{A\ln(S)T}/ε)$, where $A$ is the total number of actions that the learner can possibly take, $S$ is the number of the learner's possible reduced strategies, and $T$ is the number of trials. On each trial, the time complexity of our algorithm is, up to a factor logarithmic in the maximum number of actions at an infoset, equal to the time required for the server to transmit the reduced strategy to the user. We note that local differential privacy is the strongest version of differential privacy and, to the best of our knowledge, this is the first work to study differential privacy of any form in the extensive-form bandit problem.
title Differential Privacy in the Extensive-Form Bandit Problem
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2605.05266