A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization-Reference-Cited by-同舟云学术

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

Author:

Yi Xinlei¹,Zhang Shengjun²,Yang Tao³,Chai Tianyou³,Johansson Karl Henrik¹

Affiliation:

1. School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Decision and Control Systems,Sweden

2. University of North Texas,Department of Electrical Engineering,Denton,TX,USA,76203

3. State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University,Shenyang,China,110819

Funder

Knut and Alice Wallenberg Foundation

Swedish Foundation for Strategic Research

Swedish Research Council

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Artificial Intelligence,Information Systems,Control and Systems Engineering,Control and Optimization

Link

Reference63 articles.

1. Local SGD converges fast and communicates little;stich;Proc Int Conf Learning Representations,0

2. Decentralized stochastic gradient tracking for empirical risk minimization;zhang;ArXiv Preprint,2019

3. Quantized decentralized stochastic learning over directed graphs;taheri;Proc Int Conf Machine Learning,0

4. Robust and communication-efficient collaborative learning;reisizadeh;Advances in neural information processing systems,0

5. Communication compression for decentralized training;tang;Advances in neural information processing systems,0

Cited by 15 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

4. Robust Multitask Learning With Sample Gradient Similarity;IEEE Transactions on Systems, Man, and Cybernetics: Systems;2024-01