English

EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks

Machine Learning 2018-12-07 v3

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.

Keywords

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

R2 v1 2026-06-23T00:26:02.286Z