paper-with-me

홈 › Papers

From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD

2026-05-25 · Christoph H. Lampert, Hossein Zakerinia arxiv

Understanding the relationship between generalization and privacy remains a central challenge in modern machine learning theory, particularly for deep networks trained by variants of differentially private stochastic gradient descent (DP-SGD). In this work we make progress on this persistent open problem by proving a finite-sample bound on the approximate max-information of DP-SGD that exhibits scaling properties comparable with (Dwork et al, 2015)'s classic result for $ε$-differentially private algorithms, namely at most linear in the dataset size. From our result we obtain a general-purpose PAC-Bayes generalization bound in which the necessary prior distribution can be learned by DP-SGD, as well as a generalization bound for DP-SGD-trained models themselves, with a complexity term that is fully explicit and controlled by the optimization hyperparameters.

📄 PDF Abstract BibTeX arXiv:2605.26222

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generalization in Federated Learning: A Conditional Mutual Information Framework

2025-03-06 · Ziqiao Wang, Cheng Long, Yongyi Mao

Federated learning (FL) is a widely adopted privacy-preserving distributed learning framework, yet its generalization performance remains less explored compared to centralized learning. In FL, the generalization error co…

Federated LearningPrivacy Preserving

A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning

2026-05-05 · Dario Filatrella, Ragnar Thobaben, Mikael Skoglund arxiv

We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized framework in which data is sampled hierarchically, and we model it with a…

Federated Learning

An Information-Theoretic Approach to Generalization Theory

2024-08-20 · Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund

We investigate the in-distribution generalization of machine learning algorithms. We depart from traditional complexity-based approaches by analyzing information-theoretic bounds that quantify the dependence between a le…

On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms

2016-05-08 · Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg

We define On-Average KL-Privacy and present its properties and connections to differential privacy, generalization and information-theoretic quantities including max-information and mutual information. The new definition…

Privacy Implies Stability: Information-Theoretic Generalization Bounds for Quantum Learning

2026-02-01 · Ayanava Dasgupta, Naqueeb Ahmad Warsi, Masahito Hayashi arxiv

We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms. Learning procedures are modeled as quantum instruments with classical-quantum outputs, and …