Regularization properties of dual subgradient flow

Authors Vassilis Apidopoulos, Cesare Molinari, Lorenzo Rosasco, Silvia Villa

Publication date 11 May 2023

Evolution inclusions (34G25) Applications of operator theory in optimization, convex analysis, mathematical programming, economics (47N10) Numerical methods involving duality (49M29) Convex programming (90C25)

Abstract: Dual gradient descent combined with early stopping represents an efficient alternative to the Tikhonov variational approach when the regularizer is strongly convex. However, for many relevant applications, it is crucial to deal with regularizers which are only convex. In this setting, the dual problem is non smooth, and dual gradient descent cannot be used. In this paper, we study the regularization properties of a subgradient dual flow, and we show that the proposed procedure achieves the same recovery accuracy as penalization methods, while being more efficient from the computational perspective.

This page was built for publication: Regularization properties of dual subgradient flow

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6436236)