English
Related papers

Related papers: Local Differential Privacy for Bayesian Optimizati…

200 papers

We consider the privacy-preserving machine learning (ML) setting where the trained model must satisfy differential privacy (DP) with respect to the labels of the training examples. We propose two novel approaches based on, respectively, the…

Machine Learning · Computer Science 2021-11-02 Mani Malek , Ilya Mironov , Karthik Prasad , Igor Shilov , Florian Tramèr

In this paper, we study differentially private online learning problems in a stochastic environment under both bandit and full information feedback. For differentially private stochastic bandits, we propose both UCB and Thompson…

Machine Learning · Computer Science 2024-05-31 Bingshan Hu , Zhiming Huang , Nishant A. Mehta , Nidhi Hegde

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). We propose DP-TS-UCB,…

Machine Learning · Computer Science 2025-06-06 Bingshan Hu , Zhiming Huang , Tianyue H. Zhang , Mathias Lécuyer , Nidhi Hegde

Bayesian optimisation requires fitting a Gaussian process model, which in turn requires specifying prior on the unknown black-box function -- most of the theoretical literature assumes this prior is known. However, it is common to have more…

Machine Learning · Computer Science 2025-02-25 Juliusz Ziomek , Masaki Adachi , Michael A. Osborne

Motivated by personalized healthcare and other applications involving sensitive data, we study online exploration in reinforcement learning with differential privacy (DP) constraints. Existing work on this problem established that no-regret…

Machine Learning · Computer Science 2023-02-23 Dan Qiao , Yu-Xiang Wang

Gaussian process upper confidence bound (GP-UCB) is a theoretically promising approach for black-box optimization; however, the confidence parameter $\beta$ is considerably large in the theorem and chosen heuristically in practice. Then,…

Machine Learning · Computer Science 2023-06-13 Shion Takeno , Yu Inatsu , Masayuki Karasuyama

Differential privacy (DP) is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are built upon one of two underlying tools: Laplace and Gaussian…

Machine Learning · Computer Science 2026-04-03 Roy Rinberg , Ilia Shumailov , Vikrant Singhal , Rachel Cummings , Nicolas Papernot

Bayesian optimization (BO) is a powerful paradigm for optimizing expensive black-box functions. Traditional BO methods typically rely on separate hand-crafted acquisition functions and surrogate models for the underlying function, and often…

Machine Learning · Computer Science 2025-07-10 Fengxue Zhang , Yuxin Chen

Recommendation systems rely heavily on users behavioural and preferential data (e.g. ratings, likes) to produce accurate recommendations. However, users experience privacy concerns due to unethical data aggregation and analytical practices…

Machine Learning · Computer Science 2021-03-09 Jeyamohan Neera , Xiaomin Chen , Nauman Aslam , Kezhi Wang , Zhan Shu

We study locally differentially private (LDP) bandits learning in this paper. First, we propose simple black-box reduction frameworks that can solve a large family of context-free bandits learning problems with LDP guarantee. Based on our…

Machine Learning · Computer Science 2021-01-18 Kai Zheng , Tianle Cai , Weiran Huang , Zhenguo Li , Liwei Wang

Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the…

Machine Learning · Computer Science 2025-03-04 Zhiqi Bu , Ruixuan Liu

In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single $(\varepsilon, \delta)$-pair. This practice overlooks that DP guarantees can vary…

Cryptography and Security · Computer Science 2025-05-06 Georgios Kaissis , Stefan Kolek , Borja Balle , Jamie Hayes , Daniel Rueckert

In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting. Since the server receives more…

Machine Learning · Computer Science 2020-07-06 Xiaoyu Chen , Kai Zheng , Zixin Zhou , Yunchang Yang , Wei Chen , Liwei Wang

In this work we consider the problem of online submodular maximization under a cardinality constraint with differential privacy (DP). A stream of $T$ submodular functions over a common finite ground set $U$ arrives online, and at each…

Machine Learning · Computer Science 2020-10-27 Sebastian Perez-Salazar , Rachel Cummings

As machine learning (ML) becomes more prevalent in human-centric applications, there is a growing emphasis on algorithmic fairness and privacy protection. While previous research has explored these areas as separate objectives, there is a…

Machine Learning · Computer Science 2024-02-19 Songjie Xie , Youlong Wu , Jiaxuan Li , Ming Ding , Khaled B. Letaief

We study regret minimization in finite horizon tabular Markov decision processes (MDPs) under the constraints of differential privacy (DP). This is motivated by the widespread applications of reinforcement learning (RL) in real-world…

Machine Learning · Computer Science 2021-12-21 Sayak Ray Chowdhury , Xingyu Zhou

We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy…

Machine Learning · Computer Science 2020-03-26 Aleksei Triastcyn , Boi Faltings

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…

Many applications require a learner to make sequential decisions given uncertainty regarding both the system's payoff function and safety constraints. In safety-critical systems, it is paramount that the learner's actions do not violate the…

Machine Learning · Computer Science 2020-05-06 Sanae Amani , Mahnoosh Alizadeh , Christos Thrampoulidis

Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be…

Cryptography and Security · Computer Science 2020-11-19 Mark Cesar , Ryan Rogers