• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - Request a copy

Model Selection with Piecewise Regular Gauges

Peyré, Gabriel; Fadili, Jalal; Vaiter, Samuel; Golbabaee, Mohammad (2013), Model Selection with Piecewise Regular Gauges. https://basepub.dauphine.fr/handle/123456789/11553

Type
Document de travail / Working paper
Date
2013
Series title
Preprints Ceremade
Pages
53
Metadata
Show full item record
Author(s)
Peyré, Gabriel
Fadili, Jalal
Vaiter, Samuel cc
Golbabaee, Mohammad
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 piecewise regular gauges. These are convex, non-negative, closed, bounded and positively homogenous functions that will promote objects living on low-dimensional subspaces. This class of regularizers encompasses many popular examples such as the L^1 norm, L^1-L^2 norm (group sparsity), nuclear norm, as well as several others including the L^inf norm. We will show that the set of piecewise regular gauges is closed under addition and pre-composition by a linear operator, which allows to cover mixed regularization (e.g. sparse+low-rank), and the so-called analysis-type priors (e.g. total variation, fused Lasso, trace Lasso, bounded 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.
Subjects / Keywords
Inverse problems; Model selection; Sparsity; Piecewise regular gauge; Convex regularization; Noise robustness

Related items

Showing items related by title and author.

  • Thumbnail
    Model Selection with Low Complexity Priors 
    Vaiter, Samuel; Golbabaee, Mohammad; Fadili, Jalal; Peyré, Gabriel (2015) Article accepté pour publication ou publié
  • Thumbnail
    Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection 
    Fadili, Jalal; Peyré, Gabriel; Vaiter, Samuel; Deledalle, Charles-Alban (2014) Article accepté pour publication ou publié
  • Thumbnail
    Reconstruction Stable par Régularisation Décomposable Analyse 
    Vaiter, Samuel; Fadili, Jalal; Deledalle, Charles-Alban; Salmon, Joseph; Peyré, Gabriel (2014) Communication / Conférence
  • Thumbnail
    Robustesse au bruit des régularisations polyhédrales 
    Vaiter, Samuel; Peyré, Gabriel; Fadili, Jalal (2013) Communication / Conférence
  • Thumbnail
    Model Consistency of Partly Smooth Regularizers 
    Vaiter, Samuel; Fadili, Jalal; Peyré, Gabriel (2018) Article accepté pour publication ou publié
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo