Skip to content
Open access

Online Decision Making with Local Differential Privacy

Nov 2026 · Operational Research · 0 citations

TL;DR

This paper designs LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings, and exploits the flexibility of stochastic gradient descent (SGD), whose theoretical guarantee for bandit problems is rarely explored.

Abstract

Contextual bandit algorithms are useful in personalized online decision-making. However, many applications, such as personalized medicine and online advertising, require the utilization of user-specific information for effective learning while maintaining user privacy due to privacy concerns. This motivates the introduction of local differential privacy (LDP), a stringent notion of privacy, to contextual bandits. In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings. Our main idea is to develop a stochastic gradient-based estimator and an update mechanism to ensure LDP. We then exploit the flexibility of stochastic gradient descent (SGD), whose theoretical guarantee for bandit problems is rarely explored, to address generalized linear bandits. We further conduct experiments using both simulated and real-world datasets to demonstrate the consistently superior performance of our algorithms under LDP constraints, with reasonably small LDP parameters (ε, δ) to ensure strong privacy protection.

Read PDF

Similar papers

#large language models Open access Oct 2026

Differential Privacy Tradeoffs in Large-Scale ML Model Training

This paper introduces DPOptimizer, a privacy budget allocation framework that maximizes model utility for a given privacy budget through adaptive noise calibration, layer-wise privacy amplification, and optimal composition strategies, and provides the first systematic analysis of how the privacy-utility-compute trilemm...

S. Soni, Rinku Vedu Patili, Pritam Samanta et al. · 0 citations
Preprint Nov 2026

On the Order of Privacy and Smoothing in Functional Mean Estimation

Differential privacy (DP) is a leading framework for privacy protection, yet privacy mechanisms tailored to functional data analysis (FDA) remain relatively underexplored. For functional mean estimation, we investigate a fundamental question regarding the ordering of privatization and estimation by comparing two canoni...

Hao-Tian Chen, Yu-Wei Chen, Qi-Fan Song et al. · 0 citations
Preprint Oct 2026

Diffusion Sensitivity Geometry and Strong Duality for Optimal Privacy-Utility Tradeoffs

A framework for the optimal privacy-utility tradeoff of ideal diffusion denoisers is developed, replacing conservative bounds with exact sensitivity characterizations and provably optimal noise calibration, and exact privacy guarantees for R\'enyi, approximate, and Gaussian differential privacy are obtained.

Tue Do, Daniel Alabi · 0 citations
Preprint Oct 2026

Lower bounds for Bayesian CVaR in interactive problems with local differential privacy

We develop an information-theoretic method for lower bounding the prior-predictive conditional value-at-risk (CVaR) of loss in interactive statistical decision making (ISDM). A generalized Fano inequality replaces a single error event by a randomized binary statistic constructed from a bounded transform of the loss, re...

Raghav Bongole, A. Zamani, T. Oechtering et al. · 0 citations
Preprint Nov 2026

PLDP-IDS: Personalized Local Differential Privacy for Infinite Data Stream

PLPD and PLPA are developed, which combine group-aware population scheduling with bias-aware cross-group fusion while preserving personalized $w-event LDP and are shown to be more accurate than PLPA under strong privacy--data correlation.

Lei-Lei Du, Yi-Kun Hu, Xu Zhou et al. · 0 citations
Review Oct 2026

Learning Sparse Support under Differential Privacy: Adaptive Algorithms and Minimax Limits

Saturated Propose-test-release, a general mechanism that privately releases the output of a discrete selector with probability one once its stability certificate reaches a finite threshold, is introduced and a computable support-stability score is constructed.

Jian-Zhong Gu, T. Cai · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.