Federated Learning via Inexact ADMM
share
One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full devices participation and/or impose strong assumptions for convergence. Different from the widely-used gradient descent-based algorithms, this paper develops 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.
READ FULL TEXT