English
Related papers

Related papers: Near-Optimal Differentially Private Reinforcement …

200 papers

In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret…

Machine Learning · Statistics 2024-08-21 Xiaofeng Lin , Xuezhou Zhang

While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is limited. In particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the…

Quantum Physics · Physics 2024-06-14 Han Zhong , Jiachen Hu , Yecheng Xue , Tongyang Li , Liwei Wang

We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly…

Machine Learning · Computer Science 2021-09-07 Chen-Yu Wei , Haipeng Luo

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the…

Machine Learning · Computer Science 2023-06-29 Zihan Zhang , Qiaomin Xie

Deep Reinforcement Learning (DRL) policies have been shown to be vulnerable to small adversarial noise in observations. Such adversarial noise can have disastrous consequences in safety-critical environments. For instance, a self-driving…

Machine Learning · Computer Science 2024-03-28 Roman Belaire , Pradeep Varakantham , Thanh Nguyen , David Lo

Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels. However,…

Machine Learning · Computer Science 2018-10-26 Peter Jin , Kurt Keutzer , Sergey Levine

Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requires computation of per-sample gradients norms which is…

Machine Learning · Computer Science 2021-02-08 Zhiqi Bu , Sivakanth Gopi , Janardhan Kulkarni , Yin Tat Lee , Judy Hanwen Shen , Uthaipon Tantipongpipat

Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely unexplored. In this…

Machine Learning · Computer Science 2025-03-04 Puning Zhao , Chuan Ma , Li Shen , Shaowei Wang , Rongfei Fan

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

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

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia

Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all…

Machine Learning · Computer Science 2024-07-22 Adrian Müller , Pragnya Alatur , Volkan Cevher , Giorgia Ramponi , Niao He

Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differentially private pipeline…

Machine Learning · Statistics 2026-03-25 Young Hyun Cho , Will Wei Sun

The collection of individuals' data has become commonplace in many industries. Local differential privacy (LDP) offers a rigorous approach to preserving privacy whereby the individual privatises their data locally, allowing only their…

Machine Learning · Computer Science 2022-05-17 Alex Mansbridge , Gregory Barbour , Davide Piras , Michael Murray , Christopher Frye , Ilya Feige , David Barber

Preserving privacy in contemporary NLP models allows us to work with sensitive data, but unfortunately comes at a price. We know that stricter privacy guarantees in differentially-private stochastic gradient descent (DP-SGD) generally…

Computation and Language · Computer Science 2023-02-01 Manuel Senge , Timour Igamberdiev , Ivan Habernal

We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m…

Machine Learning · Computer Science 2021-12-06 Daniel Levy , Ziteng Sun , Kareem Amin , Satyen Kale , Alex Kulesza , Mehryar Mohri , Ananda Theertha Suresh

We study the classic problem of prediction with expert advice under the constraint of local differential privacy (LDP). In this context, we first show that a classical algorithm naturally satisfies LDP and then design two new algorithms…

Machine Learning · Computer Science 2025-12-09 Ben Jacobsen , Kassem Fawaz

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

We revisit the problem of linear regression under a differential privacy constraint. By consolidating existing pieces in the literature, we clarify the correct dependence of the feature, label and coefficient domains in the optimization…

Machine Learning · Statistics 2018-07-10 Yu-Xiang Wang

Differentially private gradient descent (DP-GD) is a popular algorithm to train deep learning models with provable guarantees on the privacy of the training data. In the last decade, the problem of understanding its performance cost with…

Machine Learning · Statistics 2025-05-29 Simone Bombari , Marco Mondelli
‹ Prev 1 3 4 5 6 7 10 Next ›