English
Related papers

Related papers: Mixing Times and Privacy Analysis for the Projecte…

200 papers

We propose a novel theoretical and methodological framework for Gaussian process regression subject to privacy constraints. The proposed method can be used when a data owner is unwilling to share a high-fidelity supervised learning model…

Machine Learning · Computer Science 2025-10-14 Rui Tuo , Haoyuan Chen , Raktim Bhattacharya

We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety-critical applications, e.g. in medical diagnosis. We…

Algorithmic stability is an important notion that has proven powerful for deriving generalization bounds for practical algorithms. The last decade has witnessed an increasing number of stability bounds for different algorithms applied on…

Machine Learning · Statistics 2023-10-31 Lingjiong Zhu , Mert Gurbuzbalaban , Anant Raj , Umut Simsekli

We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to drift approximations under the assumption that the potential…

Machine Learning · Statistics 2025-09-01 Marien Renaud , Valentin De Bortoli , Arthur Leclaire , Nicolas Papadakis

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

Privacy preservation is becoming an increasingly important issue in data mining and machine learning. In this paper, we consider the privacy preserving features of distributed subgradient optimization algorithms. We first show that a…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-12-31 Youcheng Lou , Lean Yu , Shouyang Wang

Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models.…

Machine Learning · Computer Science 2025-09-30 Saleh Vatan Khah , Savelii Chezhegov , Shahrokh Farahmand , Samuel Horváth , Eduard Gorbunov

Fingerprinting arguments, first introduced by Bun, Ullman, and Vadhan (STOC 2014), are the most widely used method for establishing lower bounds on the sample complexity or error of approximately differentially private (DP) algorithms.…

Cryptography and Security · Computer Science 2024-07-08 Naty Peter , Eliad Tsfadia , Jonathan Ullman

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

Introducing noise in the training of machine learning systems is a powerful way to protect individual privacy via differential privacy guarantees, but comes at a cost to utility. This work looks at whether the inherent randomness of…

Machine Learning · Computer Science 2022-03-01 Stephanie L. Hyland , Shruti Tople

We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP…

Data Structures and Algorithms · Computer Science 2021-10-27 Sivakanth Gopi , Yin Tat Lee , Lukas Wutschitz

In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning…

Machine Learning · Computer Science 2021-07-13 Mehdi Amian

We study the mixing time of Metropolis-Adjusted Langevin algorithm (MALA) for sampling a target density on $\mathbb{R}^d$. We assume that the target density satisfies $\psi_\mu$-isoperimetry and that the operator norm and trace of its…

Machine Learning · Statistics 2023-06-09 Yuansi Chen , Khashayar Gatmiry

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…

Machine Learning · Computer Science 2023-11-30 Jie Fu , Qingqing Ye , Haibo Hu , Zhili Chen , Lulu Wang , Kuncan Wang , Xun Ran

In this study, we investigate the performance of the Metropolis-adjusted Langevin algorithm in a setting with constraints on the support of the target distribution. We provide a rigorous analysis of the resulting Markov chain, establishing…

Computation · Statistics 2023-05-16 Jinyuan Chang , Cheng Yong Tang , Yuanzheng Zhu

Differentially Private Stochastic Gradient Descent (DP-SGD) and its variants have been proposed to ensure rigorous privacy for fine-tuning large-scale pre-trained language models. However, they rely heavily on the Gaussian mechanism, which…

Cryptography and Security · Computer Science 2024-05-30 Qin Yang , Meisam Mohammad , Han Wang , Ali Payani , Ashish Kundu , Kai Shu , Yan Yan , Yuan Hong

Noisy gradient descent and its variants are the predominant algorithms for differentially private machine learning. It is a fundamental question to quantify their privacy leakage, yet tight characterizations remain open even in the…

Machine Learning · Computer Science 2024-06-13 Jinho Bok , Weijie Su , Jason M. Altschuler

Balancing privacy and accuracy is a major challenge in designing differentially private machine learning algorithms. One way to improve this tradeoff for free is to leverage the noise in common data operations that already use randomness.…

Machine Learning · Computer Science 2021-10-20 Jacob Imola , Kamalika Chaudhuri

Data integration and sharing maximally enhance the potential for novel and meaningful discoveries. However, it is a non-trivial task as integrating data from multiple sources can put sensitive information of study participants at risk. To…

Cryptography and Security · Computer Science 2020-05-25 Yeongjae Gil , Xiaoqian Jiang , Miran Kim , Junghye Lee

Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity, non-independent, and identically distributed (Non-IID) data often…

Artificial Intelligence · Computer Science 2026-02-20 Jin Wang , Hui Ma , Fei Xing , Ming Yan