paper-with-me

홈 › Papers

Straggler-Resilient Differentially-Private Decentralized Learning

2022-12-06 · Yauhen Yakimenka, Chung-Wei Weng, Hsuan-Yin Lin, Eirik Rosnes, Jörg Kliewer

We consider the straggler problem in decentralized learning over a logical ring while preserving user data privacy. Especially, we extend the recently proposed framework of differential privacy (DP) amplification by decentralization by Cyffers and Bellet to include overall training latency--comprising both computation and communication latency. Analytical results on both the convergence speed and the DP level are derived for both a skipping scheme (which ignores the stragglers after a timeout) and a baseline scheme that waits for each node to finish before the training continues. A trade-off between overall training latency, accuracy, and privacy, parameterized by the timeout of the skipping scheme, is identified and empirically validated for logistic regression on a real-world dataset and for image classification using the MNIST and CIFAR-10 datasets.

📄 PDF Abstract BibTeX arXiv:2212.03080

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classificationregression

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning

2026-02-25 · Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang arxiv

Differentially private federated learning faces a fundamental tension: privacy protection mechanisms that safeguard client data simultaneously create quantifiable privacy costs that discourage participation, undermining …

Federated Learning

Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates

2023-06-11 · Guojun Xiong, Gang Yan, Shiqiang Wang, Jian Li

With the increasing demand for large-scale training of machine learning models, fully decentralized optimization methods have recently been advocated as alternatives to the popular parameter server framework. In this par…

Differentially Private Linear Regression over Fully Decentralized Datasets

2020-04-16 · Yang Liu, Xiong Zhang, Shuqi Qin, Xiaoping Lei

This paper presents a differentially private algorithm for linear regression learning in a decentralized fashion. Under this algorithm, privacy budget is theoretically derived, in addition to that the solution error is s…

regression

Improved Differentially Private Decentralized Source Separation for fMRI Data

2019-10-28 · Hafiz Imtiaz, Jafar Mohammadi, Rogers Silva, Bradley Baker 외

Blind source separation algorithms such as independent component analysis (ICA) are widely used in the analysis of neuroimaging data. In order to leverage larger sample sizes, different data holders/sites may wish to col…

blind source separation

Distributed Differentially Private Computation of Functions with Correlated Noise

2019-04-22 · Hafiz Imtiaz, Jafar Mohammadi, Anand D. Sarwate

Many applications of machine learning, such as human health research, involve processing private or sensitive information. Privacy concerns may impose significant hurdles to collaboration in scenarios where there are mul…

BIG-bench Machine LearningPrivacy Preserving