Locally Private Nonparametric Contextual Multi-armed Bandits

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ma, Yuheng, Jiang, Feiyu, Zhao, Zifeng, Yang, Hanfang, Yu, Yi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912292236427264
author Ma, Yuheng
Jiang, Feiyu
Zhao, Zifeng
Yang, Hanfang
Yu, Yi
author_facet Ma, Yuheng
Jiang, Feiyu
Zhao, Zifeng
Yang, Hanfang
Yu, Yi
contents Motivated by privacy concerns in sequential decision-making on sensitive data, we address the challenge of nonparametric contextual multi-armed bandits (MAB) under local differential privacy (LDP). We develop a uniform-confidence-bound-type estimator, showing its minimax optimality supported by a matching minimax lower bound. We further consider the case where auxiliary datasets are available, subject also to (possibly heterogeneous) LDP constraints. Under the widely-used covariate shift framework, we propose a jump-start scheme to effectively utilize the auxiliary data, the minimax optimality of which is further established by a matching lower bound. Comprehensive experiments on both synthetic and real-world datasets validate our theoretical results and underscore the effectiveness of the proposed methods.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Locally Private Nonparametric Contextual Multi-armed Bandits
Ma, Yuheng
Jiang, Feiyu
Zhao, Zifeng
Yang, Hanfang
Yu, Yi
Machine Learning
Methodology
Motivated by privacy concerns in sequential decision-making on sensitive data, we address the challenge of nonparametric contextual multi-armed bandits (MAB) under local differential privacy (LDP). We develop a uniform-confidence-bound-type estimator, showing its minimax optimality supported by a matching minimax lower bound. We further consider the case where auxiliary datasets are available, subject also to (possibly heterogeneous) LDP constraints. Under the widely-used covariate shift framework, we propose a jump-start scheme to effectively utilize the auxiliary data, the minimax optimality of which is further established by a matching lower bound. Comprehensive experiments on both synthetic and real-world datasets validate our theoretical results and underscore the effectiveness of the proposed methods.
title Locally Private Nonparametric Contextual Multi-armed Bandits
topic Machine Learning
Methodology
url https://arxiv.org/abs/2503.08098