Second-Order Stochastic Optimization for Machine Learning in Linear Time
Machine Learning
2017-12-01 v5 Machine Learning
Abstract
First-order stochastic methods are the state-of-the-art in large-scale machine learning optimization owing to efficient per-iteration complexity. Second-order methods, while able to provide faster convergence, have been much less explored due to the high cost of computing the second-order information. In this paper we develop second-order stochastic methods for optimization problems in machine learning that match the per-iteration cost of gradient based methods, and in certain settings improve upon the overall running time over popular first-order methods. Furthermore, our algorithm has the desirable property of being implementable in time linear in the sparsity of the input data.
Cite
@article{arxiv.1602.03943,
title = {Second-Order Stochastic Optimization for Machine Learning in Linear Time},
author = {Naman Agarwal and Brian Bullins and Elad Hazan},
journal= {arXiv preprint arXiv:1602.03943},
year = {2017}
}