Skip to main content

Second-order stochastic optimization for machine learning in linear time

Author(s): Agarwal, N; Bullins, B; Hazan, Elad

To refer to this page use:
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
Publication Date: 1-Nov-2017
Electronic Publication Date: 1-Nov-2017
Citation: Agarwal, N, Bullins, B, Hazan, E. (2017). Second-order stochastic optimization for machine learning in linear time. Journal of Machine Learning Research, 18 (1 - 40
Pages: 1 - 40
Type of Material: Journal Article
Journal/Proceeding Title: Journal of Machine Learning Research
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.