Convex relaxations of structured matrix factorizations - Inria - Institut national de recherche en sciences et technologies du numérique
Preprints, Working Papers, ... Year : 2013

Convex relaxations of structured matrix factorizations

Abstract

We consider the factorization of a rectangular matrix $X $ into a positive linear combination of rank-one factors of the form $u v^\top$, where $u$ and $v$ belongs to certain sets $\mathcal{U}$ and $\mathcal{V}$, that may encode specific structures regarding the factors, such as positivity or sparsity. In this paper, we show that computing the optimal decomposition is equivalent to computing a certain gauge function of $X$ and we provide a detailed analysis of these gauge functions and their polars. Since these gauge functions are typically hard to compute, we present semi-definite relaxations and several algorithms that may recover approximate decompositions with approximation guarantees. We illustrate our results with simulations on finding decompositions with elements in $\{0,1\}$. As side contributions, we present a detailed analysis of variational quadratic representations of norms as well as a new iterative basis pursuit algorithm that can deal with inexact first-order oracles.
Fichier principal
Vignette du fichier
struct_decomposition_hal.pdf (325.35 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00861118 , version 1 (12-09-2013)

Identifiers

Cite

Francis Bach. Convex relaxations of structured matrix factorizations. 2013. ⟨hal-00861118⟩
298 View
913 Download

Altmetric

Share

More