Variance Reduced Diffusion Adaptation for Online Learning over Networks

Mengfei Zhang, Danqi Jin, Jie Chen

科研成果: 书/报告/会议事项章节会议稿件同行评审

2 引用 (Scopus)

摘要

The stochastic variance reduced gradient (SVRG) algorithm has shown its effectiveness in accelerating the convergence of stochastic gradient algorithms. Considering the emergent applications of distributed estimation, it is interesting to investigate the way to adapt this algorithm to distributed learning with streaming data. For this purpose, in this work we first propose a time-averaging SVRG algorithm that fits into the context of streaming data processing. Then, we integrate this algorithm with the diffusion adaptation to enhance the performance of distributed estimation over networks. Theoretical analysis of the resulted algorithm is conducted to characterize its stability. We also provide the simulation results to illustrate its favorable performance.

源语言英语
主期刊名ICSPCC 2020 - IEEE International Conference on Signal Processing, Communications and Computing, Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781728172019
DOI
出版状态已出版 - 21 8月 2020
活动2020 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2020 - Macau, 中国
期限: 21 8月 202023 8月 2020

出版系列

姓名ICSPCC 2020 - IEEE International Conference on Signal Processing, Communications and Computing, Proceedings

会议

会议2020 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2020
国家/地区中国
Macau
时期21/08/2023/08/20

指纹

探究 'Variance Reduced Diffusion Adaptation for Online Learning over Networks' 的科研主题。它们共同构成独一无二的指纹。

引用此