English
Related papers

Related papers: Locally Differentially Private Thresholding Bandit…

200 papers

We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal $\tilde{O}(\sqrt{T})$ regret bounds. In the full-information setting, our results demonstrate…

Machine Learning · Computer Science 2017-06-15 Naman Agarwal , Karan Singh

Best Arm Identification (BAI) algorithms are deployed in data-sensitive applications, such as adaptive clinical trials or user studies. Driven by the privacy concerns of these applications, we study the problem of fixed-confidence BAI under…

Machine Learning · Statistics 2025-10-21 Marc Jourdan , Achraf Azize

While pursuing better utility by discovering knowledge from the data, individual's privacy may be compromised during an analysis. To that end, differential privacy has been widely recognized as the state-of-the-art privacy notion. By…

Cryptography and Security · Computer Science 2022-09-07 Meisam Mohammady

In the past decade analysis of big data has proven to be extremely valuable in many contexts. Local Differential Privacy (LDP) is a state-of-the-art approach which allows statistical computations while protecting each individual user's…

Cryptography and Security · Computer Science 2019-07-30 Björn Bebensee

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 by adding noise at…

Machine Learning · Statistics 2021-10-28 Tejas Kulkarni , Joonas Jälkö , Samuel Kaski , Antti Honkela

Multi-armed bandit algorithms are fundamental tools for sequential decision-making under uncertainty, with widespread applications across domains such as clinical trials and personalized decision-making. As bandit algorithms are…

Machine Learning · Computer Science 2025-08-07 Dhruv Sarkar , Nishant Pandey , Sayak Ray Chowdhury

The private collection of multiple statistics from a population is a fundamental statistical problem. One possible approach to realize this is to rely on the local model of differential privacy (LDP). Numerous LDP protocols have been…

Cryptography and Security · Computer Science 2023-08-02 Héber H. Arcolezi , Sébastien Gambs , Jean-François Couchot , Catuscia Palamidessi

Data that is gathered adaptively --- via bandit algorithms, for example --- exhibits bias. This is true both when gathering simple numeric valued data --- the empirical means kept track of by stochastic bandit algorithms are biased…

Machine Learning · Computer Science 2018-06-07 Seth Neel , Aaron Roth

We study the best-arm identification problem in multi-armed bandits with stochastic, potentially private rewards, when the goal is to identify the arm with the highest quantile at a fixed, prescribed level. First, we propose a (non-private)…

Machine Learning · Statistics 2022-12-06 Kontantinos E. Nikolakakis , Dionysios S. Kalogerias , Or Sheffet , Anand D. Sarwate

Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the…

Machine Learning · Computer Science 2025-02-03 Alexandre Rio , Merwan Barlier , Igor Colin

We design new differentially private algorithms for the problems of adversarial bandits and bandits with expert advice. For adversarial bandits, we give a simple and efficient conversion of any non-private bandit algorithm to a private…

Machine Learning · Computer Science 2025-05-29 Hilal Asi , Vinod Raman , Kunal Talwar

We present a new locally differentially private algorithm for the heavy hitters problem which achieves optimal worst-case error as a function of all standardly considered parameters. Prior work obtained error rates which depend optimally on…

Data Structures and Algorithms · Computer Science 2017-11-15 Mark Bun , Jelani Nelson , Uri Stemmer

In this work we first show that the classical Thompson sampling algorithm for multi-arm bandits is differentially private as-is, without any modification. We provide per-round privacy guarantees as a function of problem parameters and show…

Machine Learning · Computer Science 2024-07-23 Tingting Ou , Marco Avella Medina , Rachel Cummings

Differential Privacy (DP) provides a rigorous framework for privacy, ensuring the outputs of data-driven algorithms remain statistically indistinguishable across datasets that differ in a single entry. While guaranteeing DP generally…

Machine Learning · Computer Science 2025-10-17 Yizhou Zhang , Kishan Panaganti , Laixi Shi , Juba Ziani , Adam Wierman

This paper studies \emph{differential privacy (DP)} and \emph{local differential privacy (LDP)} in cascading bandits. Under DP, we propose an algorithm which guarantees $\epsilon$-indistinguishability and a regret of…

Machine Learning · Computer Science 2021-06-07 Kun Wang , Jing Dong , Baoxiang Wang , Shuai Li , Shuo Shao

Shuffle model of differential privacy is a novel distributed privacy model based on a combination of local privacy mechanisms and a secure shuffler. It has been shown that the additional randomisation provided by the shuffler improves…

Cryptography and Security · Computer Science 2022-02-02 Antti Koskela , Mikko A. Heikkilä , Antti Honkela

We study locally differentially private algorithms for reinforcement learning to obtain a robust policy that performs well across distributed private environments. Our algorithm protects the information of local agents' models from being…

Machine Learning · Computer Science 2020-02-03 Hajime Ono , Tsubasa Takahashi

Private collection of statistics from a large distributed population is an important problem, and has led to large scale deployments from several leading technology companies. The dominant approach requires each user to randomly perturb…

Databases · Computer Science 2021-11-10 Graham Cormode , Samuel Maddock , Carsten Maple

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

Local differential privacy is a differential privacy paradigm in which individuals first apply a privacy mechanism to their data (often by adding noise) before transmitting the result to a curator. The noise for privacy results in…

Methodology · Statistics 2023-10-17 Yuki Ohnishi , Jordan Awan