Anderson acceleration of gradient methods with energy for optimization problems
Optimization and Control
2022-11-17 v1
Abstract
Anderson acceleration (AA) as an efficient technique for speeding up the convergence of fixed-point iterations may be designed for accelerating an optimization method. We propose a novel optimization algorithm by adapting Anderson acceleration to the energy adaptive gradient method (AEGD) [arXiv:2010.05109]. The feasibility of our algorithm is examined in light of convergence results for AEGD, though it is not a fixed-point iteration. We also quantify the accelerated convergence rate of AA for gradient descent by a factor of the gain at each implementation of the Anderson mixing. Our experimental results show that the proposed algorithm requires little tuning of hyperparameters and exhibits superior fast convergence.
Cite
@article{arxiv.2211.08578,
title = {Anderson acceleration of gradient methods with energy for optimization problems},
author = {Hailiang Liu and Jia-Hao He and Xuping Tian},
journal= {arXiv preprint arXiv:2211.08578},
year = {2022}
}
Comments
18 pages, 4 figures