A Unified Framework for Stochastic Matrix Factorization via Variance Reduction

Renbo Zhao; William B Haskell; Jiashi Feng

doi:10.48550/arxiv.1705.06884

Back

A Unified Framework for Stochastic Matrix Factorization via Variance Reduction

Preprint

Open access

A Unified Framework for Stochastic Matrix Factorization via Variance Reduction

Renbo Zhao, William B Haskell and Jiashi Feng

ArXiv.org

Cornell University

05/19/2017

DOI: 10.48550/arxiv.1705.06884

Files and links (1)

url

https://doi.org/10.48550/arXiv.1705.06884View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

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 ϵ-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-à-vis state-of-the-art frameworks.

Machine Learning

Optimization and Control

Details

Title: Subtitle: A Unified Framework for Stochastic Matrix Factorization via Variance Reduction
Creators: Renbo Zhao
William B Haskell
Jiashi Feng
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.1705.06884
ISSN: 2331-8422
Publisher: Cornell University
Language: English
Date posted: 05/19/2017
Academic Unit: Business Analytics
Record Identifier: 9984446731902771

Metrics

18 Record Views