On Representer Theorems and Convex Regularization

DOI10.1137/18M1200750zbMath1423.49036arXiv1806.09810OpenAlexW2809809415WikidataQ127901703 ScholiaQ127901703MaRDI QIDQ5231664

Vincent Duval, Antonin Chambolle, Yohann de Castro, Pierre Weiss, Claire Boyer, Frédéric de Gournay

Publication date: 27 August 2019

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.09810

zbMATH Keywords

total variationinverse problemsvector spaceconvex regularizationrepresenter theorem

Mathematics Subject Classification ID

Spaces of measures (46E27) Inverse problems in optimal control (49N45)

Related Items (37)

Towards off-the-grid algorithms for total variation regularized inverse problems ⋮ A superposition principle for the inhomogeneous continuity equation with Hellinger–Kantorovich-regular coefficients ⋮ Two-Layer Neural Networks with Values in a Banach Space ⋮ Sparse optimization on measures with over-parameterized gradient descent ⋮ A Generative Variational Model for Inverse Problems in Imaging ⋮ Convex optimization in sums of Banach spaces ⋮ Sparse regularized learning in the reproducing kernel Banach spaces with the \(\ell^1\) norm ⋮ ``FISTA in Banach spaces with adaptive discretisations ⋮ Linear inverse problems with nonnegativity constraints: singularity of optimisers ⋮ A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization ⋮ Off-the-Grid Curve Reconstruction through Divergence Regularization: An Extreme Point Result ⋮ Dynamical programming for off-the-grid dynamic inverse problems ⋮ Unnamed Item ⋮ Asymptotic linear convergence of fully-corrective generalized conditional gradient methods ⋮ Linear inverse problems with Hessian-Schatten total variation ⋮ An Epigraphical Approach to the Representer Theorem ⋮ The Geometry of Sparse Analysis Regularization ⋮ Functions with bounded Hessian-Schatten variation: density, variational, and extremality properties ⋮ Atomic norm minimization for decomposition into complex exponentials and optimal transport in Fourier domain ⋮ TV-based reconstruction of periodic functions ⋮ Higher-order total variation approaches and generalisations ⋮ Non-smooth Variational Regularization for Processing Manifold-Valued Data ⋮ A unifying representer theorem for inverse problems and machine learning ⋮ Towards off-the-grid algorithms for total variation regularized inverse problems ⋮ On the linear convergence rates of exchange and continuous methods for total variation minimization ⋮ Unnamed Item ⋮ Energy on spheres and discreteness of minimizing measures ⋮ Structural analysis of an \(L\)-infinity variational problem and relations to distance functions ⋮ Sparsity of solutions for variational inverse problems with finite-dimensional data ⋮ Block-based refitting in \(\ell_{12}\) sparse regularization ⋮ Functional penalised basis pursuit on spheres ⋮ Multiview attenuation estimation and correction ⋮ Sparsest piecewise-linear regression of one-dimensional data ⋮ An optimal transport approach for solving dynamic inverse problems in spaces of measures ⋮ TV-based spline reconstruction with Fourier measurements: uniqueness and convergence of grid-based methods ⋮ Understanding neural networks with reproducing kernel Banach spaces ⋮ On the extremal points of the ball of the Benamou–Brenier energy

Cites Work

• Nonlinear total variation based noise removal algorithms
• Extreme point inequalities and geometry of the rank sparsity ball
• Generalized sampling and infinite-dimensional compressed sensing
• Extremal structure of convex sets
• Functions with generalized gradient and generalized surfaces
• Understanding and using linear programming
• Exact support recovery for sparse spikes deconvolution
• Spline solutions to L\(^1\) extremal problems in one and several variables
• Problems of distance geometry and convex properties of quadratic maps
• The convex geometry of linear inverse problems
• A first-order primal-dual algorithm for convex problems with applications to imaging
• Sparsity of solutions for variational inverse problems with finite-dimensional data
• On extreme points of convex sets
• On a theorem of Dubins
• Some remarks on the class of continuous (semi-)strictly quasiconvex functions
• The operator theory of the pseudo-inverse. I: Bounded operators, II: Unbounded operators with arbitrary range
• Exact matrix completion via convex optimization
• Representer Theorems for Sparsity-Promoting <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math> </inline-formula> Regularization
• Exact Solutions to Super Resolution on Semi-Algebraic Domains in Higher Dimensions
• Blind Deconvolution Using Convex Programming
• Espaces vectoriels topologiques
• Local Strong Homogeneity of a Regularized Estimator
• Splines Are Universal Solutions of Linear Inverse Problems with Generalized TV Regularization
• Super-resolution of point sources via convex programming
• Continuous-Domain Solutions of Linear Inverse Problems With Tikhonov Versus Generalized TV Regularization
• Compressed Sensing Off the Grid
• Sparse nonnegative solution of underdetermined linear equations by linear programming
• Towards a Mathematical Theory of Super‐resolution
• The maximum numbers of faces of a convex polytope
• On the approximation of real functions in the sense of P. L. Čebyšev
• Scattered Data Approximation
• Compressed sensing
• Connected components of sets of finite perimeter and applications to image processing
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: On Representer Theorems and Convex Regularization