Reconciling "priors" and "priors" without prejudice? - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Reconciling "priors" and "priors" without prejudice?

Abstract

There are two major routes to address linear inverse problems. Whereas regularization-based approaches build estimators as solutions of penalized regression optimization problems, Bayesian estimators rely on the posterior distribution of the unknown, given some assumed family of priors. While these may seem radically different approaches, recent results have shown that, in the context of additive white Gaussian denoising, the Bayesian conditional mean estimator is always the solution of a penalized regression problem. The contribution of this paper is twofold. First, we extend the additive white Gaussian denoising results to general linear inverse problems with colored Gaussian noise. Second, we characterize conditions under which the penalty function associated to the conditional mean estimator can satisfy certain popular properties such as convexity, separability, and smoothness. This sheds light on some tradeoff between computational efficiency and estimation accuracy in sparse regularization, and draws some connections between Bayesian estimation and proximal optimization.
Fichier principal
Vignette du fichier
NIPS2013_4868.pdf (134.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00918008 , version 1 (12-12-2013)

Identifiers

  • HAL Id : hal-00918008 , version 1

Cite

Rémi Gribonval, Pierre Machart. Reconciling "priors" and "priors" without prejudice?. Advances in Neural Information Processing Systems, Dec 2013, South Lake Tahoe, United States. ⟨hal-00918008⟩
213 View
105 Download

Share

Gmail Facebook X LinkedIn More