Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization
Statistical preconditioning enables fast methods for distributed large-scale empirical risk minimization problems. In this approach, multiple worker nodes compute gradients in parallel, which are then used by the central node to update the parameter by solving an auxiliary (preconditioned) smaller-s...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-01-01
|
Series: | EURO Journal on Computational Optimization |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2192440622000211 |