Model Selection with Low Complexity Priors
Vaiter, Samuel; Golbabaee, Mohammad; Fadili, Jalal; Peyré, Gabriel (2015), Model Selection with Low Complexity Priors, Information and Inference, 4, 3, p. 230-287. 10.1093/imaiai/iav005
Type
Article accepté pour publication ou publiéExternal document link
https://arxiv.org/abs/1307.2342v2Date
2015Journal name
Information and InferenceVolume
4Number
3Pages
230-287
Publication identifier
Metadata
Show full item recordAuthor(s)
Vaiter, Samuel
Golbabaee, Mohammad
Fadili, Jalal
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Peyré, Gabriel
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)
Regularization plays a pivotal role when facing the challenge of solving ill-posed inverse problems, where the number of observations is smaller than the ambient dimension of the object to be estimated. A line of recent work has studied regularization models with various types of low-dimensional structures. In such settings, the general approach is to solve a regularized optimization problem, which combines a data fidelity term and some regularization penalty that promotes the assumed low-dimensional/simple structure. This paper provides a general framework to capture this low-dimensional structure through what we coin partly smooth functions relative to a linear manifold. These are convex, non-negative, closed and finite-valued functions that will promote objects living on low-dimensional subspaces. This class of regularizers encompasses many popular examples such as the L1 norm, L1-L2 norm (group sparsity), as well as several others including the Linfty norm. We also show that the set of partly smooth functions relative to a linear manifold is closed under addition and pre-composition by a linear operator, which allows to cover mixed regularization, and the so-called analysis-type priors (e.g. total variation, fused Lasso, finite-valued polyhedral gauges). Our main result presents a unified sharp analysis of exact and robust recovery of the low-dimensional subspace model associated to the object to recover from partial measurements. This analysis is illustrated on a number of special and previously studied cases, and on an analysis of the performance of Linfty regularization in a compressed sensing scenario.Subjects / Keywords
Sparsity; Partial smoothness; Inverse problems; Compressed Sensing; onvex regularization; Model selection; Total variationRelated items
Showing items related by title and author.
-
Peyré, Gabriel; Fadili, Jalal; Vaiter, Samuel; Golbabaee, Mohammad (2013) Document de travail / Working paper
-
Vaiter, Samuel; Peyré, Gabriel; Fadili, Jalal (2015) Chapitre d'ouvrage
-
Salmon, Joseph; Deledalle, Charles-Alban; Vaiter, Samuel; Peyré, Gabriel; Fadili, Jalal (2013) Communication / Conférence
-
Fadili, Jalal; Peyré, Gabriel; Vaiter, Samuel; Deledalle, Charles-Alban (2014) Article accepté pour publication ou publié
-
Vaiter, Samuel; Fadili, Jalal; Peyré, Gabriel (2018) Article accepté pour publication ou publié