Iterative regularization for low complexity regularizers
From MaRDI portal
Abstract: Iterative regularization exploits the implicit bias of an optimization algorithm to regularize ill-posed problems. Constructing algorithms with such built-in regularization mechanisms is a classic challenge in inverse problems but also in modern machine learning, where it provides both a new perspective on algorithms analysis, and significant speed-ups compared to explicit regularization. In this work, we propose and study the first iterative regularization procedure able to handle biases described by non smooth and non strongly convex functionals, prominent in low-complexity regularization. Our approach is based on a primal-dual algorithm of which we analyze convergence and stability properties, even in the case where the original problem is unfeasible. The general results are illustrated considering the special case of sparse recovery with the penalty. Our theoretical results are complemented by experiments showing the computational benefits of our approach.
Recommendations
- Iterative regularization via dual diagonal descent
- Iterative regularization with a general penalty term-theory and application to \(L^{1}\) and \(TV\) regularization
- Fast iterative regularization by reusing data
- Low complexity regularization of linear inverse problems
- Irregularization accelerates iterative regularization
This page was built for publication: Iterative regularization for low complexity regularizers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6389834)
