Locally Differentially Private Thresholding Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barbara, Annalisa, Lazzaro, Joseph, Pike-Burke, Ciara
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918129481809920
author Barbara, Annalisa
Lazzaro, Joseph
Pike-Burke, Ciara
author_facet Barbara, Annalisa
Lazzaro, Joseph
Pike-Burke, Ciara
contents This work investigates the impact of ensuring local differential privacy in the thresholding bandit problem. We consider both the fixed budget and fixed confidence settings. We propose methods that utilize private responses, obtained through a Bernoulli-based differentially private mechanism, to identify arms with expected rewards exceeding a predefined threshold. We show that this procedure provides strong privacy guarantees and derive theoretical performance bounds on the proposed algorithms. Additionally, we present general lower bounds that characterize the additional loss incurred by any differentially private mechanism, and show that the presented algorithms match these lower bounds up to poly-logarithmic factors. Our results provide valuable insights into privacy-preserving decision-making frameworks in bandit problems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_23073
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Locally Differentially Private Thresholding Bandits
Barbara, Annalisa
Lazzaro, Joseph
Pike-Burke, Ciara
Machine Learning
This work investigates the impact of ensuring local differential privacy in the thresholding bandit problem. We consider both the fixed budget and fixed confidence settings. We propose methods that utilize private responses, obtained through a Bernoulli-based differentially private mechanism, to identify arms with expected rewards exceeding a predefined threshold. We show that this procedure provides strong privacy guarantees and derive theoretical performance bounds on the proposed algorithms. Additionally, we present general lower bounds that characterize the additional loss incurred by any differentially private mechanism, and show that the presented algorithms match these lower bounds up to poly-logarithmic factors. Our results provide valuable insights into privacy-preserving decision-making frameworks in bandit problems.
title Locally Differentially Private Thresholding Bandits
topic Machine Learning
url https://arxiv.org/abs/2507.23073