Fast Curvature Matrix-Vector Products
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Hi-index | 0.00 |
We propose a generic method for iteratively approximating various second-order gradient steps - Newton, Gauss-Newton, Levenberg-Marquardt, and natural gradient - in linear time per iteration, using special curvature matrix-vector products that can be computed in O(n). Two recent acceleration techniques for online learning, matrix momentum and stochastic meta-descent (SMD), in fact implement this approach. Since both were originally derived by very different routes, this offers fresh insight into their operation, resulting in further improvements to SMD.