all AI news
Momentum Approximation in Asynchronous Private Federated Learning
Feb. 15, 2024, 5:42 a.m. | Tao Yu, Congzheng Song, Jianyu Wang, Mona Chitnis
cs.LG updates on arXiv.org arxiv.org
Abstract: Asynchronous protocols have been shown to improve the scalability of federated learning (FL) with a massive number of clients. Meanwhile, momentum-based methods can achieve the best model quality in synchronous FL. However, naively applying momentum in asynchronous FL algorithms leads to slower convergence and degraded model performance. It is still unclear how to effective combinie these two techniques together to achieve a win-win. In this paper, we find that asynchrony introduces implicit bias to momentum …
abstract algorithms approximation arxiv asynchronous convergence cs.lg federated learning leads massive performance quality scalability type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Data Science Analyst
@ Mayo Clinic | AZ, United States
Sr. Data Scientist (Network Engineering)
@ SpaceX | Redmond, WA