Subsampled online matrix factorization with convergence guarantees - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Subsampled online matrix factorization with convergence guarantees

Abstract

We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i.e., that contains more than 1TB of data). The algorithm streams the matrix columns while subsampling them, resulting in low complexity per iteration and reasonable memory footprint. In contrast to previous online matrix factorization methods, our approach relies on low-dimensional statistics from past iterates to control the extra variance introduced by subsampling. We present a convergence analysis that guarantees us to reach a stationary point of the problem. Large speed-ups can be obtained compared to previous online algorithms that do not perform subsampling, thanks to the feature redundancy that often exists in high-dimensional settings.
Fichier principal
Vignette du fichier
modl_opt.pdf (356.91 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01405058 , version 1 (30-11-2016)

Identifiers

  • HAL Id : hal-01405058 , version 1

Cite

Arthur Mensch, Julien Mairal, Gaël Varoquaux, Bertrand Thirion. Subsampled online matrix factorization with convergence guarantees. NIPS Workshop on Optimization for Machine Learning, Dec 2016, Barcelone, Spain. ⟨hal-01405058⟩
846 View
234 Download

Share

Gmail Facebook X LinkedIn More