Consistency analysis of bilevel data-driven learning in inverse problems

Neil Kumar Chada, Claudia Schillings, Xin T. Tong, Simon Weissmann

Research output: Contribution to journalArticlepeer-review

Abstract

One fundamental problem when solving inverse problems is how to find regularization parameters. This article considers solving this problem using data-driven bilevel optimization, i.e. we consider the adaptive learning of the regularization parameter from data by means of optimization. This approach can be interpreted as solving an empirical risk minimization problem, and we analyze its performance in the large data sample size limit for general nonlinear problems. We demonstrate how to implement our framework on linear inverse problems, where we can further show that the inverse accuracy does not depend on the ambient space dimension. To reduce the associated computational cost, online numerical schemes are derived using the stochastic gradient descent method. We prove convergence of these numerical schemes under suitable assumptions on the forward problem. Numerical experiments are presented illustrating the theoretical results and demonstrating the applicability and efficiency of the proposed approaches for various linear and nonlinear inverse problems, including Darcy flow, the eikonal equation, and an image denoising example.
Original languageEnglish (US)
Pages (from-to)123-164
Number of pages42
JournalCommunications in Mathematical Sciences
Volume20
Issue number1
DOIs
StatePublished - Dec 10 2021

ASJC Scopus subject areas

  • Applied Mathematics
  • Mathematics(all)

Fingerprint

Dive into the research topics of 'Consistency analysis of bilevel data-driven learning in inverse problems'. Together they form a unique fingerprint.

Cite this