Tracking the Gradients Using the Hessian: A New Look at Variance Reducing Stochastic Methods
Abstract
Our goal is to improve variance reducing stochastic methods through better control variates. We first propose a modification of SVRG which uses the Hessian to track gradients over time, rather than to recondition, increasing the correlation of the control variates and leading to faster theoretical convergence close to the optimum. We then propose accurate and computationally efficient approximations to the Hessian, both using a diagonal and a low-rank matrix. Finally, we demonstrate the effectiveness of our method on a wide range of problems.
Cite
Text
Gower et al. "Tracking the Gradients Using the Hessian: A New Look at Variance Reducing Stochastic Methods." International Conference on Artificial Intelligence and Statistics, 2018.Markdown
[Gower et al. "Tracking the Gradients Using the Hessian: A New Look at Variance Reducing Stochastic Methods." International Conference on Artificial Intelligence and Statistics, 2018.](https://mlanthology.org/aistats/2018/gower2018aistats-tracking/)BibTeX
@inproceedings{gower2018aistats-tracking,
title = {{Tracking the Gradients Using the Hessian: A New Look at Variance Reducing Stochastic Methods}},
author = {Gower, Robert M. and Le Roux, Nicolas and Bach, Francis R.},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2018},
pages = {707-715},
url = {https://mlanthology.org/aistats/2018/gower2018aistats-tracking/}
}