EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks
Abstract
For training fully-connected neural networks (FCNNs), we propose a practical approximate second-order method including: 1) an approximation of the Hessian matrix and 2) a conjugate gradient (CG) based method. Our proposed approximate Hessian matrix is memory-efficient and can be applied to any FCNNs where the activation and criterion functions are twice differentiable. We devise a CG-based method incorporating one-rank approximation to derive Newton directions for training FCNNs, which significantly reduces both space and time complexity. This CG-based method can be employed to solve any linear equation where the coefficient matrix is Kronecker-factored, symmetric and positive definite. Empirical studies show the efficacy and efficiency of our proposed method.
Cite
@article{arxiv.1802.06502,
title = {EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks},
author = {Sheng-Wei Chen and Chun-Nan Chou and Edward Y. Chang},
journal= {arXiv preprint arXiv:1802.06502},
year = {2018}
}
Comments
Change to AAAI-19 Version