Photo by hajjidirir from unsplash
One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence.… Click to show full abstract
One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence. Different from the widely-used gradient descent-based algorithms, in this paper, we develop an inexact alternating direction method of multipliers (ADMM), which is both computation- and communication-efficient, capable of combating the stragglers' effect, and convergent under mild conditions. Furthermore, it has high numerical performance compared with several state-of-the-art algorithms for federated learning.
Journal Title: IEEE transactions on pattern analysis and machine intelligence
Year Published: 2022
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!