Risk estimation for matrix recovery with spectral regularization - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Risk estimation for matrix recovery with spectral regularization

Abstract

In this paper, we develop an approach to recursively estimate the quadratic risk for matrix recovery problems regularized with spectral functions. Toward this end, in the spirit of the SURE theory, a key step is to compute the (weak) derivative and divergence of a solution with respect to the observations. As such a solution is not available in closed form, but rather through a proximal splitting algorithm, we propose to recursively compute the divergence from the sequence of iterates. A second challenge that we unlocked is the computation of the (weak) derivative of the proximity operator of a spectral function. To show the potential applicability of our approach, we exemplify it on a matrix completion problem to objectively and automatically select the regularization parameter.
Fichier principal
Vignette du fichier
icml2012.pdf (151.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00695326 , version 1 (07-05-2012)
hal-00695326 , version 2 (23-10-2012)
hal-00695326 , version 3 (31-10-2012)

Identifiers

Cite

Charles-Alban Deledalle, Samuel Vaiter, Gabriel Peyré, Jalal M. Fadili, Charles H Dossal. Risk estimation for matrix recovery with spectral regularization. ICML'2012 workshop on Sparsity, Dictionaries and Projections in Machine Learning and Signal Processing, Jun 2012, Edinburgh, United Kingdom. ⟨hal-00695326v3⟩
569 View
200 Download

Altmetric

Share

Gmail Facebook X LinkedIn More