paper-with-me

Papers

Local Differential Privacy for Bayesian Optimization

2020-10-13 · Xingyu Zhou, Jian Tan

Motivated by the increasing concern about privacy in nowadays data-intensive online learning systems, we consider a black-box optimization in the nonparametric Gaussian process setting with local differential privacy (LDP) guarantee. Specifically, the rewards from each user are further corrupted to protect privacy and the learner only has access to the corrupted rewards to minimize the regret. We first derive the regret lower bounds for any LDP mechanism and any learning algorithm. Then, we present three almost optimal algorithms based on the GP-UCB framework and Laplace DP mechanism. In this process, we also propose a new Bayesian optimization (BO) method (called MoMA-GP-UCB) based on median-of-means techniques and kernel approximations, which complements previous BO algorithms for heavy-tailed payoffs with a reduced complexity. Further, empirical comparisons of different algorithms on both synthetic and real-world datasets highlight the superior performance of MoMA-GP-UCB in both private and non-private scenarios.

📄 PDF Abstract BibTeX arXiv:2010.06709

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Optimization

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

Scalable Differentially Private Bayesian Optimization

2025-02-09 · Getoar Sopa, Juraj Marusic, Marco Avella-Medina, John P. Cunningham

In recent years, there has been much work on scaling Bayesian Optimization to high-dimensional problems, for example hyperparameter tuning in large machine learning models. These scalable methods have been successful, fi…

Bayesian Optimization

Differentially Private Federated Bayesian Optimization with Distributed Exploration

2021-10-27 · NeurIPS 2021 12 · Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet

Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm, which has promising applications such as federated hyperparameter tuning. H…

Bayesian OptimizationFederated LearningThompson Sampling

Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy

2024-10-24 · Maryam Aliakbarpour, Syomantak Chaudhuri, Thomas A. Courtade, Alireza Fallah 외

Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. However, LDP applies uniform protection to all data features, including less sensitive ones, which degr…

Locally Differentially Private Bayesian Inference

2021-10-27 · tejas kulkarni, Joonas Jälkö, Samuel Kaski, Antti Honkela

In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy …

Bayesian Inferenceparameter estimationPrivacy PreservingUncertainty Quantification

Differentially Private Bayesian Optimization

2015-01-16 · Matt J. Kusner, Jacob R. Gardner, Roman Garnett, Kilian Q. Weinberger

Bayesian optimization is a powerful tool for fine-tuning the hyper-parameters of a wide variety of machine learning models. The success of machine learning has led practitioners in diverse real-world settings to learn cl…

Bayesian OptimizationBIG-bench Machine Learning