Fast iterative regularization by reusing data

TL;DR

This paper introduces two new iterative regularization methods leveraging redundant information about the solution set, improving efficiency and stability in solving inverse problems with non-smooth, non-strongly convex regularizers.

Contribution

It proposes novel primal-dual based iterative regularization algorithms that reuse data using a priori knowledge, with theoretical convergence, stability guarantees, and practical advantages demonstrated.

Findings

Convergence rates established for noise-free case.

Stability bounds and early-stopping rules with guarantees.

Numerical results show improved performance in sparse recovery and image reconstruction.

Abstract

Discrete inverse problems correspond to solving a system of equations in a stable way with respect to noise in the data. A typical approach to enforce uniqueness and select a meaningful solution is to introduce a regularizer. While for most applications the regularizer is convex, in many cases it is not smooth nor strongly convex. In this paper, we propose and study two new iterative regularization methods, based on a primal-dual algorithm, to solve inverse problems efficiently. Our analysis, in the noise free case, provides convergence rates for the Lagrangian and the feasibility gap. In the noisy case, it provides stability bounds and early-stopping rules with theoretical guarantees. The main novelty of our work is the exploitation of some a priori knowledge about the solution set, i.e. redundant information. More precisely we show that the linear systems can be used more than once along the iteration. Despite the simplicity of the idea, we show that this procedure brings surprising advantages in the numerical applications. We discuss various approaches to take advantage of redundant information, that are at the same time consistent with our assumptions and flexible in the implementation. Finally, we illustrate our theoretical findings with numerical simulations for robust sparse recovery and image reconstruction through total variation. We confirm the efficiency of the proposed procedures, comparing the results with state-of-the-art methods.