Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks-Reference-Cited by-同舟云学术

Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks

Author:

Song Zhuoqing¹^ORCID,Shi Lei²,Pu Shi³^ORCID,Yan Ming⁴^ORCID

Affiliation:

1. Shanghai Center for Mathematical Sciences, Fudan University, Shanghai, China

2. School of Mathematical Sciences, Shanghai Key Laboratory for Contemporary Applied Mathematics, Fudan University, Shanghai, China

3. School of Data Science, Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China

4. Department of Computational Mathematics, Science and Engineering and Department of Mathematics, Michigan State University, East Lansing, MI, USA

Funder

Shanghai Science and Technology Program

National Natural Science Foundation of China

Shenzhen Research Institute of Big Data

National Science Foundation

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Signal Processing

Link

Reference67 articles.

1. Doublesqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression;tang;Proc Int Conf Mach Learn,0

2. Sparsified SGD with memory;stich;Proc Adv Neural Inf Process Syst,0

4. Error feedback fixes signsgd and other gradient compression schemes;karimireddy;Proc Int Conf Mach Learn,0

5. On biased compression for distributed learning;beznosikov,2020

Cited by 8 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

1. A Compressed Decentralized Federated Learning Framework for Enhanced Environmental Awareness in V2V Networks;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14