Sparsity of solutions for variational inverse problems with finite-dimensional data

Abstract

In this paper we characterize sparse solutions for variational problems of the form ${\min }_{u\in X}\varphi (u)+F(\mathcal{A}u)$, where $X$ is a locally convex space, $\mathcal{A}$ is a linear continuous operator that maps into a finite dimensional Hilbert space and $\varphi$ is a seminorm. More precisely, we prove that there exists a minimizer that is `sparse' in the sense that it is represented as a linear combination of the extremal points of the unit ball associated with the regularizer $\varphi$ (possibly translated by an element in the null space of $\varphi$). We apply this result to relevant regularizers such as the total variation seminorm and the Radon norm of a scalar linear differential operator. In the first example, we provide a theoretical justification of the so-called staircase effect and in the second one, we recover the result in [31] under weaker hypotheses.

References in corpus (4)

• The Convex Geometry of Linear Inverse Problems
• Geometric properties of solutions to the total variation denoising problem
• Splines are Universal Solutions of Linear Inverse Problems with Generalized-TV regularization
• The least error method for sparse solution reconstruction

Cited by in corpus (20)

• Higher-order total variation approaches and generalisations
• A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization
• On the extremal points of the ball of the Benamou-Brenier energy
• An optimal transport approach for solving dynamic inverse problems in spaces of measures
• Asymptotic linear convergence of fully-corrective generalized conditional gradient methods
• A superposition principle for the inhomogeneous continuity equation with Hellinger-Kantorovich-regular coefficients
• Structural analysis of an $L$-infinity variational problem and relations to distance functions
• Exact recovery of the support of piecewise constant images via total variation regularization
• Regularisation, optimisation, subregularity
• A Fast and Scalable Polyatomic Frank-Wolfe Algorithm for the LASSO
• Towards Off-the-grid Algorithms for Total Variation Regularized Inverse Problems
• Extremal points and sparse optimization for generalized Kantorovich-Rubinstein norms
• Conditional gradients for total variation regularization with PDE constraints: a graph cuts approach
• Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
• Weighted variation spaces and approximation by shallow ReLU networks
• Distributional Extension and Invertibility of the $k$-Plane Transform and Its Dual
• Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities
• Sparse Source Identification in Transient Advection-Diffusion Problems with a Primal-Dual-Active-Point Strategy
• Sparsity for dynamic inverse problems on Wasserstein curves with bounded variation
• On extreme points and representer theorems for the Lipschitz unit ball on finite metric spaces