A Unified Framework for Stochastic Matrix Factorization via Variance Reduction
Machine Learning
2017-05-23 v2 Machine Learning
Optimization and Control
Abstract
We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction. Our framework is general and it subsumes several well-known SMF formulations in the literature. We perform a non-asymptotic convergence analysis of our framework and derive computational and sample complexities for our algorithm to converge to an -stationary point in expectation. In addition, extensive experiments for a wide class of SMF formulations demonstrate that our framework consistently yields faster convergence and a more accurate output dictionary vis-\`a-vis state-of-the-art frameworks.
Cite
@article{arxiv.1705.06884,
title = {A Unified Framework for Stochastic Matrix Factorization via Variance Reduction},
author = {Renbo Zhao and William B. Haskell and Jiashi Feng},
journal= {arXiv preprint arXiv:1705.06884},
year = {2017}
}