English
Related papers

Related papers: Near-Optimal Reinforcement Learning with Shuffle D…

200 papers

The offline reinforcement learning (RL) problem is often motivated by the need to learn data-driven decision policies in financial, legal and healthcare applications. However, the learned policy could retain sensitive information of…

Machine Learning · Computer Science 2023-01-04 Dan Qiao , Yu-Xiang Wang

We consider the problem of differentially private (DP) convex empirical risk minimization (ERM). While the standard DP-SGD algorithm is theoretically well-established, practical implementations often rely on shuffled gradient methods that…

Machine Learning · Computer Science 2026-02-25 Shuli Jiang , Pranay Sharma , Zhiwei Steven Wu , Gauri Joshi

We study a setting of collecting and learning from private data distributed across end users. In the shuffled model of differential privacy, the end users partially protect their data locally before sharing it, and their data is also…

Machine Learning · Computer Science 2025-02-21 Tal Wagner

Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…

Machine Learning · Computer Science 2025-02-17 Dariush Wahdany , Matthew Jagielski , Adam Dziedzic , Franziska Boenisch

Local differential privacy (LDP) enables the efficient release of aggregate statistics without having to trust the central server (aggregator), as in the central model of differential privacy, and simultaneously protects a client's…

Cryptography and Security · Computer Science 2025-04-24 Tariq Bontekoe , Hassan Jameel Asghar , Fatih Turkmen

Contextual bandit algorithms are widely used in domains where it is desirable to provide a personalized service by leveraging contextual information, that may contain sensitive information that needs to be protected. Inspired by this…

Machine Learning · Computer Science 2021-12-14 Evrard Garcelon , Kamalika Chaudhuri , Vianney Perchet , Matteo Pirotta

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy (DP) offers a principled approach for quantifying privacy…

Machine Learning · Computer Science 2026-02-04 Yinan Huang , Haoteng Yin , Eli Chien , Rongzhe Wei , Pan Li

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. Two standard approaches, privacy amplification by subsampling, and privacy amplification…

Machine Learning · Computer Science 2020-07-31 Borja Balle , Peter Kairouz , H. Brendan McMahan , Om Thakkar , Abhradeep Thakurta

In the \emph{shuffle model} of differential privacy, data-holding users send randomized messages to a secure shuffler, the shuffler permutes the messages, and the resulting collection of messages must be differentially private with regard…

Cryptography and Security · Computer Science 2020-08-13 Victor Balcer , Albert Cheu , Matthew Joseph , Jieming Mao

We consider training models with differential privacy (DP) using mini-batch gradients. The existing state-of-the-art, Differentially Private Stochastic Gradient Descent (DP-SGD), requires privacy amplification by sampling or shuffling to…

Cryptography and Security · Computer Science 2021-12-13 Peter Kairouz , Brendan McMahan , Shuang Song , Om Thakkar , Abhradeep Thakurta , Zheng Xu

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition…

Cryptography and Security · Computer Science 2020-09-16 NhatHai Phan , My T. Thai , Han Hu , Ruoming Jin , Tong Sun , Dejing Dou

Federated learning (FL) has rapidly become a compelling paradigm that enables multiple clients to jointly train a model by sharing only gradient updates for aggregation, without revealing their local private data. In order to protect the…

Cryptography and Security · Computer Science 2024-10-07 Shuangqing Xu , Yifeng Zheng , Zhongyun Hua

Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…

Machine Learning · Computer Science 2026-03-04 Caihong Qin , Yang Bai

Trustworthy federated learning aims to achieve optimal performance while ensuring clients' privacy. Existing privacy-preserving federated learning approaches are mostly tailored for image data, lacking applications for time series data,…

Machine Learning · Computer Science 2023-08-01 Chenxi Huang , Chaoyang Jiang , Zhenghua Chen

We study regret minimization under privacy constraints in episodic inhomogeneous linear Markov Decision Processes (MDPs), motivated by the growing use of reinforcement learning (RL) in personalized decision-making systems that rely on…

Machine Learning · Computer Science 2025-04-29 Sharan Sahu

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

Machine Learning · Computer Science 2025-07-31 Afshin Khadangi , Amir Sartipi , Igor Tchappi , Ramin Bahmani , Gilbert Fridgen

Motivated by high-stakes decision-making domains like personalized medicine where user information is inherently sensitive, we design privacy preserving exploration policies for episodic reinforcement learning (RL). We first provide a…

Machine Learning · Computer Science 2020-09-22 Giuseppe Vietri , Borja Balle , Akshay Krishnamurthy , Zhiwei Steven Wu

Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitive information that needs to be protected from third parties.…

Machine Learning · Computer Science 2021-10-28 Evrard Garcelon , Vianney Perchet , Ciara Pike-Burke , Matteo Pirotta

We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. While prior work on private contextual bandits has been restricted to linear reward models -- which…

Machine Learning · Statistics 2026-04-28 Sahasrajit Sarmasarkar

There has been a recent wave of interest in intermediate trust models for differential privacy that eliminate the need for a fully trusted central data collector, but overcome the limitations of local differential privacy. This interest has…

Data Structures and Algorithms · Computer Science 2020-12-07 Albert Cheu , Jonathan Ullman