Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods

Author name not available (Why is that?)

Publication date: 20 October 2017

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.

Has companion code repository: https://github.com/gowerrobert/StochOpt

Mathematics Subject Classification ID

No records found.

This page was built for publication: Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6292811)