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.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2018
- arXiv:
- arXiv:1802.06502
- Bibcode:
- 2018arXiv180206502C
- Keywords:
-
- Computer Science - Machine Learning
- E-Print:
- Change to AAAI-19 Version