Iterative regularization for convex regularizers

Cesare Molinari · Mathurin Massias · Lorenzo Rosasco · Silvia Villa

Keywords: [ Algorithms, Optimization and Computation Methods ] [ Convex optimization ]

[ Abstract ]
Thu 15 Apr 7:30 a.m. PDT — 9:30 a.m. PDT


We study iterative regularization for linear models, when the bias is convex but not necessarily strongly convex. We characterize the stability properties of a primal-dual gradient based approach, analyzing its convergence in the presence of worst case deterministic noise. As a main example, we specialize and illustrate the results for the problem of robust sparse recovery. Key to our analysis is a combination of ideas from regularization theory and optimization in the presence of errors. Theoretical results are complemented by experiments showing that state-of-the-art performances are achieved with considerable computational speed-ups.

Chat is not available.