paper-with-me

Papers

A simplified convergence theory for Byzantine resilient stochastic gradient descent

2022-08-25 · Lindon Roberts, Edward Smyth

In distributed learning, a central server trains a model according to updates provided by nodes holding local data samples. In the presence of one or more malicious servers sending incorrect information (a Byzantine adversary), standard algorithms for model training such as stochastic gradient descent (SGD) fail to converge. In this paper, we present a simplified convergence theory for the generic Byzantine Resilient SGD method originally proposed by Blanchard et al. [NeurIPS 2017]. Compared to the existing analysis, we shown convergence to a stationary point in expectation under standard assumptions on the (possibly nonconvex) objective function and flexible assumptions on the stochastic gradients.

📄 PDF Abstract BibTeX arXiv:2208.11879

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks

2019-12-29 · Zhaoxian Wu, Qing Ling, Tianyi Chen, Georgios B. Giannakis

This paper deals with distributed finite-sum optimization for learning over networks in the presence of malicious Byzantine attacks. To cope with such attacks, most resilient approaches so far combine stochastic gradient…

GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework

2025-04-24 · Yacine Belal, Mohamed Maouche, Sonia Ben Mokhtar, Anthony Simonet-Boulogne

Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent GL approaches rely on dynamic communication graphs built and m…

Model Poisoning

Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data

2020-05-16 · Deepesh Data, Suhas Diggavi

We study distributed stochastic gradient descent (SGD) in the master-worker architecture under Byzantine attacks. We consider the heterogeneous data model, where different workers may have different local datasets, and w…

Vocal Bursts Intensity Prediction

Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent

2017-12-01 · NeurIPS 2017 12 · Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, Julien Stainer

We study the resilience to Byzantine failures of distributed implementations of Stochastic Gradient Descent (SGD). So far, distributed machine learning frameworks have largely ignored the possibility of failures, especi…

BIG-bench Machine Learning

Byzantine-Resilient Secure Federated Learning

2020-07-21 · Jinhyun So, Basak Guler, A. Salman Avestimehr

Secure federated learning is a privacy-preserving framework to improve machine learning models by training over large volumes of data collected by mobile users. This is achieved through an iterative process where, at eac…

Federated LearningOutlier DetectionPrivacy PreservingQuantization