Federated Learning via Inexact ADMM
This addresses the need for more robust and efficient federated learning methods, though it appears incremental as it builds on existing ADMM approaches.
The paper tackles the problem of developing efficient optimization algorithms for federated learning by proposing an inexact ADMM method that is computation- and communication-efficient, combats stragglers' effect, and converges under mild conditions, showing high numerical performance compared to state-of-the-art algorithms.
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 a high numerical performance compared with several state-of-the-art algorithms for federated learning.