Finite-sum Composition Optimization via Variance Reduced Gradient Descent
Author(s): Lian, Xiangru; Wang, Mengdi; Liu, Ji
DownloadTo refer to this page use:
http://arks.princeton.edu/ark:/88435/pr1s19r
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lian, Xiangru | - |
dc.contributor.author | Wang, Mengdi | - |
dc.contributor.author | Liu, Ji | - |
dc.date.accessioned | 2020-02-24T22:03:10Z | - |
dc.date.available | 2020-02-24T22:03:10Z | - |
dc.date.issued | 2017-01-01 | en_US |
dc.identifier.citation | Lian, X, Wang, M, Liu, J. (2017). Finite-sum Composition Optimization via Variance Reduced Gradient Descent. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017 | en_US |
dc.identifier.uri | http://arks.princeton.edu/ark:/88435/pr1s19r | - |
dc.description.abstract | The stochastic composition optimization proposed recently by Wang et al. [2014] minimizes the objective with the compositional expectation form: minx (EiFi o EjGj)(x). It summarizes many important applications in machine learning, statistics, and finance. In this paper, we consider the finite-sum scenario for composition optimization: (Formula presented.). We propose two algorithms to solve this problem by combining the stochastic compositional gradient descent (SCGD) and the stochastic variance reduced gradient (SVRG) technique. A constant linear convergence rate is proved for strongly convex optimization, which substantially improves the sublinear rate O(K−0.8) of the best known algorithm. Copyright 2017 by the author(s). | en_US |
dc.format.extent | 1 - 30 | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartof | Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017 | en_US |
dc.rights | Final published version. This is an open access article. | en_US |
dc.title | Finite-sum Composition Optimization via Variance Reduced Gradient Descent | en_US |
dc.type | Conference Article | en_US |
dc.date.eissued | 2017-05-20 | en_US |
pu.type.symplectic | http://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceeding | en_US |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
OA_FiniteSumCompositionOptimizationVarianceReducedGradientDescent.pdf | 447.75 kB | Adobe PDF | View/Download |
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.