English
Related papers

Related papers: Byzantine-Resilient Non-Convex Stochastic Gradient…

200 papers

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

In Byzantine robust distributed or federated learning, a central server wants to train a machine learning model over data distributed across multiple workers. However, a fraction of these workers may deviate from the prescribed algorithm…

Machine Learning · Computer Science 2023-11-23 Sai Praneeth Karimireddy , Lie He , Martin Jaggi

Decentralized learning has gained great popularity to improve learning efficiency and preserve data privacy. Each computing node makes equal contribution to collaboratively learn a Deep Learning model. The elimination of centralized…

Machine Learning · Computer Science 2021-10-22 Shangwei Guo , Tianwei Zhang , Han Yu , Xiaofei Xie , Lei Ma , Tao Xiang , Yang Liu

In distributed learning, sign-based compression algorithms such as signSGD with majority vote provide a lightweight alternative to SGD with an additional advantage: fault tolerance (almost) for free. However, for signSGD with majority vote,…

Machine Learning · Computer Science 2025-03-12 Emanuele Mengoli , Luzius Moll , Virgilio Strozzi , El-Mahdi El-Mhamdi

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

Stochastic gradient descent (SGD) gives an optimal convergence rate when minimizing convex stochastic objectives $f(x)$. However, in terms of making the gradients small, the original SGD does not give an optimal rate, even when $f(x)$ is…

Machine Learning · Computer Science 2021-07-30 Zeyuan Allen-Zhu

Large-scale non-convex sparsity-constrained problems have recently gained extensive attention. Most existing deterministic optimization methods (e.g., GraSP) are not suitable for large-scale and high-dimensional problems, and thus…

Machine Learning · Computer Science 2019-12-03 Fanhua Shang , Bingkun Wei , Hongying Liu , Yuanyuan Liu , Jiacheng Zhuo

Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structures remain vulnerable to malicious influences. In this…

Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness…

Machine Learning · Computer Science 2013-01-01 Ohad Shamir , Tong Zhang

Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several…

Machine Learning · Computer Science 2019-06-10 Zhenxun Zhuang , Ashok Cutkosky , Francesco Orabona

The vulnerability of deep neural networks to small and even imperceptible perturbations has become a central topic in deep learning research. Although several sophisticated defense mechanisms have been introduced, most were later shown to…

Machine Learning · Computer Science 2021-09-28 Leo Schwinn , An Nguyen , René Raab , Dario Zanca , Bjoern Eskofier , Daniel Tenbrinck , Martin Burger

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

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

In this paper, we introduce a new stochastic approximation (SA) type algorithm, namely the randomized stochastic gradient (RSG) method, for solving an important class of nonlinear (possibly nonconvex) stochastic programming (SP) problems.…

Optimization and Control · Mathematics 2015-10-27 Saeed Ghadimi , Guanghui Lan

Distributed algorithms for multi-agent resource allocation can provide privacy and scalability over centralized algorithms in many cyber-physical systems. However, the distributed nature of these algorithms can render these systems…

Optimization and Control · Mathematics 2020-12-08 Berkay Turan , Cesar A. Uribe , Hoi-To Wai , Mahnoosh Alizadeh

This paper addresses the challenge of solving the generalized Nash Equilibrium seeking problem for decentralized stochastic online multi-cluster games amidst Byzantine agents. During the game process, each honest agent is influenced by both…

Optimization and Control · Mathematics 2025-07-31 Bingqian Liu , Guanghui Wen , Liyuan Chen , Yiguang Hong

Stochastic gradient descent (SGD) is a popular and efficient method with wide applications in training deep neural nets and other nonconvex models. While the behavior of SGD is well understood in the convex learning setting, the existing…

Machine Learning · Computer Science 2019-12-16 Yunwen Lei , Ting Hu , Guiying Li , Ke Tang

Decentralized optimization is a promising parallel computation paradigm for large-scale data analytics and machine learning problems defined over a network of nodes. This paper is concerned with decentralized non-convex composite problems…

Optimization and Control · Mathematics 2021-10-05 Ran Xin , Subhro Das , Usman A. Khan , Soummya Kar

This paper proposes SplitSGD, a new dynamic learning rate schedule for stochastic optimization. This method decreases the learning rate for better adaptation to the local geometry of the objective function whenever a stationary phase is…

Machine Learning · Statistics 2024-02-20 Matteo Sordello , Niccolò Dalmasso , Hangfeng He , Weijie Su

Byzantine-robust federated learning aims at mitigating Byzantine failures during the federated training process, where malicious participants may upload arbitrary local updates to the central server to degrade the performance of the global…

Machine Learning · Computer Science 2023-02-15 Shenghui Li , Edith C. -H. Ngai , Thiemo Voigt