Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization
Machine Learning
2018-10-30 v1 Machine Learning
Optimization and Control
Abstract
We introduce Kalman Gradient Descent, a stochastic optimization algorithm that uses Kalman filtering to adaptively reduce gradient variance in stochastic gradient descent by filtering the gradient estimates. We present both a theoretical analysis of convergence in a non-convex setting and experimental results which demonstrate improved performance on a variety of machine learning areas including neural networks and black box variational inference. We also present a distributed version of our algorithm that enables large-dimensional optimization, and we extend our algorithm to SGD with momentum and RMSProp.
Cite
@article{arxiv.1810.12273,
title = {Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization},
author = {James Vuckovic},
journal= {arXiv preprint arXiv:1810.12273},
year = {2018}
}
Comments
25 pages, 5 figures