English
Related papers

Related papers: Zeno++: Robust Fully Asynchronous SGD

200 papers

Distributed model training needs to be adapted to challenges such as the straggler effect and Byzantine attacks. When coordinating the training process with multiple computing nodes, ensuring timely and reliable gradient aggregation amidst…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-11 Jiahe Yan , Pratik Chaudhari , Leonard Kleinrock

This paper studies the problem of distributed stochastic optimization in an adversarial setting where, out of the $m$ machines which allegedly compute stochastic gradients every iteration, an $\alpha$-fraction are Byzantine, and can behave…

Machine Learning · Computer Science 2018-03-26 Dan Alistarh , Zeyuan Allen-Zhu , Jerry Li

This paper considers the Byzantine fault-tolerance problem in distributed stochastic gradient descent (D-SGD) method - a popular algorithm for distributed multi-agent machine learning. In this problem, each agent samples data points…

Machine Learning · Computer Science 2021-04-20 Nirupam Gupta , Shuo Liu , Nitin H. Vaidya

We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and behave arbitrarily to prevent an accurate model from being…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-10-24 Yudong Chen , Lili Su , Jiaming Xu

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 descent (SGD) with…

Machine Learning · Computer Science 2023-07-19 Zhaoxian Wu , Qing Ling , Tianyi Chen , Georgios B. Giannakis

In this work, we consider the resilience of distributed algorithms based on stochastic gradient descent (SGD) in distributed learning with potentially Byzantine attackers, who could send arbitrary information to the parameter server to…

Machine Learning · Computer Science 2019-09-11 Haibo Yang , Xin Zhang , Minghong Fang , Jia Liu

We address the challenges of Byzantine-robust training in asynchronous distributed machine learning systems, aiming to enhance efficiency amid massive parallelization and heterogeneous computing resources. Asynchronous systems, marked by…

Machine Learning · Computer Science 2025-06-05 Tehila Dahan , Kfir Y. Levy

Distributed learning has become a hot research topic due to its wide application in clusterbased large-scale learning, federated learning, edge computing and so on. Most traditional distributed learning methods typically assume no failure…

Machine Learning · Computer Science 2022-02-01 Yi-Rui Yang , Wu-Jun Li

Asynchronous stochastic gradient descent (SGD) is attractive from a speed perspective because workers do not wait for synchronization. However, the Transformer model converges poorly with asynchronous SGD, resulting in substantially lower…

Computation and Language · Computer Science 2021-11-30 Alham Fikri Aji , Kenneth Heafield

Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-03 El-Mahdi El-Mhamdi , Rachid Guerraoui , Arsany Guirguis , Lê Nguyên Hoang , Sébastien Rouault

In this paper, we propose a class of robust stochastic subgradient methods for distributed learning from heterogeneous datasets at presence of an unknown number of Byzantine workers. The Byzantine workers, during the learning process, may…

Machine Learning · Computer Science 2019-11-12 Liping Li , Wei Xu , Tianyi Chen , Georgios B. Giannakis , Qing Ling

Byzantine-robust learning has emerged as a prominent fault-tolerant distributed machine learning framework. However, most techniques focus on the static setting, wherein the identity of Byzantine workers remains unchanged throughout the…

Machine Learning · Computer Science 2024-06-18 Ron Dorfman , Naseem Yehya , Kfir Y. Levy

We consider the problem of Byzantine fault-tolerance in the peer-to-peer (P2P) distributed gradient-descent method -- a prominent algorithm for distributed optimization in a P2P system. In this problem, the system comprises of multiple…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-02-01 Nirupam Gupta , Nitin H. Vaidya

We tackle the problem of Byzantine errors in distributed gradient descent within the Byzantine-resilient gradient coding framework. Our proposed solution can recover the exact full gradient in the presence of $s$ malicious workers with a…

Information Theory · Computer Science 2024-01-31 Shreyas Jain , Luis Maßny , Christoph Hofmeister , Eitan Yaakobi , Rawad Bitar

Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the question of how to combine them effectively remains…

Machine Learning · Computer Science 2023-10-06 Rachid Guerraoui , Nirupam Gupta , Rafael Pinot , Sebastien Rouault , John Stephan

This paper proposes a Robust Gradient Classification Framework (RGCF) for Byzantine fault tolerance in distributed stochastic gradient descent. The framework consists of a pattern recognition filter which we train to be able to classify…

Machine Learning · Computer Science 2023-01-19 Shashank Reddy Chirra , Kalyan Varma Nadimpalli , Shrisha Rao

Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome.…

Cryptography and Security · Computer Science 2021-09-07 Yusen Wu , Hao Chen , Xin Wang , Chao Liu , Phuong Nguyen , Yelena Yesha

This paper studies Byzantine-robust stochastic optimization over a decentralized network, where every agent periodically communicates with its neighbors to exchange local models, and then updates its own local model by stochastic gradient…

Machine Learning · Computer Science 2023-08-11 Jie Peng , Weiyu Li , Qing Ling

Asynchronous stochastic gradient descent (ASGD) is a standard way to exploit heterogeneous compute resources in distributed learning: instead of forcing fast workers to wait for slow ones, the server updates the model whenever a gradient…

Machine Learning · Computer Science 2026-05-14 Ammar Mahran , Artavazd Maranjyan , Peter Richtárik

Distributed model training is vulnerable to byzantine system failures and adversarial compute nodes, i.e., nodes that use malicious updates to corrupt the global model stored at a parameter server (PS). To guarantee some form of robustness,…

Machine Learning · Statistics 2018-06-25 Lingjiao Chen , Hongyi Wang , Zachary Charles , Dimitris Papailiopoulos