English
Related papers

Related papers: Differentially Private Regret Minimization in Epis…

200 papers

The gold standard for privacy in machine learning, Differential Privacy (DP), is often interpreted through its guarantees against membership inference. However, translating DP budgets into quantitative protection against the more damaging…

Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss…

Cryptography and Security · Computer Science 2020-06-26 Jinshuo Dong , David Durfee , Ryan Rogers

We consider the problem of learning in adversarial Markov decision processes [MDPs] with an oblivious adversary in a full-information setting. The agent interacts with an environment during $T$ episodes, each of which consists of $H$…

Machine Learning · Computer Science 2025-03-06 Daniil Tiapkin , Evgenii Chzhen , Gilles Stoltz

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

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

The iterative nature of the expectation maximization (EM) algorithm presents a challenge for privacy-preserving estimation, as each iteration increases the amount of noise needed. We propose a practical private EM algorithm that overcomes…

Machine Learning · Computer Science 2016-11-01 Mijung Park , Jimmy Foulds , Kamalika Chaudhuri , Max Welling

Within the machine learning community, reconstruction attacks are a principal concern and have been identified even in federated learning (FL), which was designed with privacy preservation in mind. In response to these threats, the privacy…

Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering from high ``burn-in'' costs and…

Machine Learning · Computer Science 2026-03-26 Guy Zamir , Matthew Zurek , Yudong Chen

We study model personalization under user-level differential privacy (DP) in the shared representation framework. In this problem, there are $n$ users whose data is statistically heterogeneous, and their optimal parameters share an unknown…

Machine Learning · Computer Science 2025-06-25 Conor Snedeker , Xinyu Zhou , Raef Bassily

Local differential privacy (LDP) is increasingly employed in privacy-preserving machine learning to protect user data before sharing it with an untrusted aggregator. Most LDP methods assume that users possess only a single data record,…

Machine Learning · Computer Science 2025-05-05 Behnoosh Zamanlooy , Mario Diaz , Shahab Asoodeh

Machine learning models have shone in a variety of domains and attracted increasing attention from both the security and the privacy communities. One important yet worrying question is: Will training models under the differential privacy…

Machine Learning · Computer Science 2023-11-22 Yuan Zhang , Zhiqi Bu

Metric Differential Privacy (mDP) extends the local differential privacy (LDP) framework to metric spaces, enabling more nuanced privacy protection for data such as geo-locations. However, existing mDP optimization methods, particularly…

Cryptography and Security · Computer Science 2025-09-11 Ruiyao Liu , Chenxi Qiu

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

Differential privacy (DP) is a mathematical framework that guarantees individual privacy; however, systematic evaluation of its impact on statistical utility in survival analyses remains limited. In this study, we systematically evaluated…

Cryptography and Security · Computer Science 2026-04-24 Keita Fukuyama , Yukiko Mori , Tomohiro Kuroda , Hiroaki Kikuchi

Privacy is a growing concern in modern deep-learning systems and applications. Differentially private (DP) training prevents the leakage of sensitive information in the collected training data from the trained machine learning models. DP…

Machine Learning · Computer Science 2024-08-28 Xinwei Zhang , Zhiqi Bu , Mingyi Hong , Meisam Razaviyayn

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-02-10 Anirudh Satheesh , Vaneet Aggarwal

Online prediction from experts is a fundamental problem in machine learning and several works have studied this problem under privacy constraints. We propose and analyze new algorithms for this problem that improve over the regret bounds of…

Machine Learning · Computer Science 2023-07-03 Hilal Asi , Vitaly Feldman , Tomer Koren , Kunal Talwar

In this paper, we show that the process of continually learning new tasks and memorizing previous tasks introduces unknown privacy risks and challenges to bound the privacy loss. Based upon this, we introduce a formal definition of Lifelong…

Machine Learning · Computer Science 2022-07-27 Phung Lai , Han Hu , NhatHai Phan , Ruoming Jin , My T. Thai , An M. Chen

We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a…

Machine Learning · Computer Science 2023-03-16 Rahul Singh , Abhishek Gupta , Ness B. Shroff

The distributed nature of local differential privacy (LDP) invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular…

Cryptography and Security · Computer Science 2025-06-18 Xiaolin Li , Ninghui Li , Boyang Wang , Wenhai Sun