paper-with-me

홈 › Papers

No-Regret Algorithms for Private Gaussian Process Bandit Optimization

2021-02-24 · Abhimanyu Dubey

The widespread proliferation of data-driven decision-making has ushered in a recent interest in the design of privacy-preserving algorithms. In this paper, we consider the ubiquitous problem of gaussian process (GP) bandit optimization from the lens of privacy-preserving statistics. We propose a solution for differentially private GP bandit optimization that combines a uniform kernel approximator with random perturbations, providing a generic framework to create differentially-private (DP) Gaussian process bandit algorithms. For two specific DP settings - joint and local differential privacy, we provide algorithms based on efficient quadrature Fourier feature approximators, that are computationally efficient and provably no-regret for popular stationary kernel functions. Our algorithms maintain differential privacy throughout the optimization procedure and critically do not rely explicitly on the sample path for prediction, making the parameters straightforward to release as well.

📄 PDF Abstract BibTeX arXiv:2102.12467

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingPrivacy Preserving

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret

2025-05-05 · Bingshan Hu, Zhiming Huang, Tianyue H. Zhang, Mathias Lécuyer 외

We address differentially private stochastic bandit problems from the angles of exploring the deep connections among Thompson Sampling with Gaussian priors, Gaussian mechanisms, and Gaussian differential privacy (GDP). W…

Thompson Sampling

Differentially Private Contextual Linear Bandits

2018-09-28 · NeurIPS 2018 12 · Roshan Shariff, Or Sheffet

We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a reward which depends also on a user provided…

Differentially Private Stochastic Linear Bandits: (Almost) for Free

2022-07-07 · Osama A. Hanna, Antonious M. Girgis, Christina Fragouli, Suhas Diggavi

In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve almost the same regret as the optimal n…

Concentrated Differential Privacy for Bandits

2023-09-01 · Achraf Azize, Debabrota Basu

Bandits serve as the theoretical foundation of sequential learning and an algorithmic foundation of modern recommender systems. However, recommender systems often rely on user-sensitive data, making privacy a critical co…

Multi-Armed BanditsRecommendation Systems

(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings

2013-12-01 · NeurIPS 2013 12 · Abhradeep Guha Thakurta, Adam Smith

We provide a general technique for making online learning algorithms differentially private, in both the full information and bandit settings. Our technique applies to algorithms that aim to minimize a \emph{convex} loss…