Combining Conjugate Direction Methods with Stochastic Approximation of Gradients
Abstract
The method of conjugate directions provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to stochastic approximation of the gradient. Here we explore ideas from conjugate gradient in the stochastic (online) setting, using fast Hessian-gradient products to set up low-dimensional Krylov subspaces within individual mini-batches. In our benchmark experiments the resulting online learning algorithms converge orders of magnitude faster than ordinary stochastic gradient descent.
Cite
Text
Schraudolph and Graepel. "Combining Conjugate Direction Methods with Stochastic Approximation of Gradients." Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, 2003.Markdown
[Schraudolph and Graepel. "Combining Conjugate Direction Methods with Stochastic Approximation of Gradients." Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, 2003.](https://mlanthology.org/aistats/2003/schraudolph2003aistats-combining/)BibTeX
@inproceedings{schraudolph2003aistats-combining,
title = {{Combining Conjugate Direction Methods with Stochastic Approximation of Gradients}},
author = {Schraudolph, Nicol N. and Graepel, Thore},
booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics},
year = {2003},
pages = {248-253},
volume = {R4},
url = {https://mlanthology.org/aistats/2003/schraudolph2003aistats-combining/}
}