paper-with-me

홈 › Papers

Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning

2026-05-18 · Arnab Auddy, Xiangni Peng, Subhadeep Paul arxiv

Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for differentially private (DP) federated M estimation. The two standard methods in the literature are FedAvg, which may suffer from high federation bias, and FedSGD, which can incur high communication cost. Aimed at improving accuracy at a reduced communication cost, we propose FedHybrid, which uses FedSGD starting with an improved initialization by the FedAvg estimator. We propose FedNewton, which averages local Newton iterations to reduce bias in FedAvg, achieving an estimation accuracy comparable to FedSGD with much fewer communication rounds when the number of clients grows sufficiently slowly. We establish finite sample upper bounds on the mean-squared error rates of the DP versions of these estimators as functions of the number of clients, local sample sizes, privacy budget, and number of iterations. We further derive a minimax lower bound on the MSE of any iterative private federated procedure that provides a benchmark to assess the optimality gap of these methods. We numerically evaluate our methods for training a logistic regression and a neural network on the computer vision datasets MNIST and CIFAR-10.

📄 PDF Abstract BibTeX arXiv:2605.18656

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Differentially Private Sliced Inverse Regression: Minimax Optimality and Algorithm

2024-01-16 · Xintao Xia, Linjun Zhang, Zhanrui Cai

Privacy preservation has become a critical concern in high-dimensional data analysis due to the growing prevalence of data-driven applications. Since its proposal, sliced inverse regression has emerged as a widely utiliz…

Dimensionality Reductionregression

Differentially Private Federated Learning: A Systematic Review

2024-05-14 · Jie Fu, Yuan Hong, XinPeng Ling, Leixia Wang 외

In recent years, privacy and security concerns in machine learning have promoted trusted federated learning to the forefront of research. Differential privacy has emerged as the de facto standard for privacy protection i…

Federated LearningPrivacy Preserving

Efficient Private Algorithms for Learning Large-Margin Halfspaces

2019-02-24 · Huy L. Nguyen, Jonathan Ullman, Lydia Zakynthinou

We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or o…

Differentially Private Federated Learning with Laplacian Smoothing

2020-05-01 · Zhicong Liang, Bao Wang, Quanquan Gu, Stanley Osher 외

Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. However, an adversary may still be able to infer the private training data by attacking the re…

Federated Learning

Differentially-Private Federated Linear Bandits

2020-10-22 · NeurIPS 2020 12 · Abhimanyu Dubey, Alex Pentland

The rapid proliferation of decentralized learning systems mandates the need for differentially-private cooperative learning. In this paper, we study this in context of the contextual linear bandit: we consider a collecti…

Federated Learning