paper-with-me

Papers

cpSGD: Communication-efficient and differentially-private distributed SGD

2018-05-27 · NeurIPS 2018 12 · Naman Agarwal, Ananda Theertha Suresh, Felix Yu, Sanjiv Kumar, H. Brendan McMahan

Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy of the clients. Several recent works have focused on reducing the communication cost or introducing privacy guarantees, but none of the proposed communication efficient methods are known to be privacy preserving and none of the known privacy mechanisms are known to be communication efficient. To this end, we study algorithms that achieve both communication efficiency and differential privacy. For $d$ variables and $n \approx d$ clients, the proposed method uses $O(\log \log(nd))$ bits of communication per client per coordinate and ensures constant privacy. We also extend and improve previous analysis of the \emph{Binomial mechanism} showing that it achieves nearly the same utility as the Gaussian mechanism, while requiring fewer representation bits, which can be of independent interest.

📄 PDF Abstract BibTeX arXiv:1805.10559

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

Scalable and Provably Accurate Algorithms for Differentially Private Distributed Decision Tree Learning

2020-12-19 · Kaiwen Wang, Travis Dick, Maria-Florina Balcan

This paper introduces the first provably accurate algorithms for differentially private, top-down decision tree learning in the distributed setting (Balcan et al., 2012). We propose DP-TopDown, a general privacy preservi…

Privacy Preserving

Differentially Private Linear Bandits with Partial Distributed Feedback

2022-07-12 · Fengjiao Li, Xingyu Zhou, Bo Ji

In this paper, we study the problem of global reward maximization with only partial distributed feedback. This problem is motivated by several real-world applications (e.g., cellular network configuration, dynamic pricin…

High-Dimensional Differentially Private Quantile Regression: Distributed Estimation and Statistical Inference

2025-08-07 · Ziliang Shen, Caixing Wang, Shaoli Wang, Yibo Yan arxiv

With the development of big data and machine learning, privacy concerns have become increasingly critical, especially when handling heterogeneous datasets containing sensitive personal information. Differential privacy p…

Multi-Message Shuffled Privacy in Federated Learning

2023-02-22 · Antonious M. Girgis, Suhas Diggavi

We study differentially private distributed optimization under communication constraints. A server using SGD for optimization aggregates the client-side local gradients for model updates using distributed mean estimation…

Distributed OptimizationFederated LearningOpen-Ended Question Answering

Differentially Private Distributed Online Learning

2015-05-25 · Chencheng Li, Pan Zhou

Online learning has been in the spotlight from the machine learning society for a long time. To handle massive data in Big Data era, one single learner could never efficiently finish this heavy task. Hence, in this paper…