Don't relax: early stopping for convex regularization
arXiv:1707.05422
Abstract
We consider the problem of designing efficient regularization algorithms when regularization is encoded by a (strongly) convex functional. Unlike classical penalization methods based on a relaxation approach, we propose an iterative method where regularization is achieved via early stopping. Our results show that the proposed procedure achieves the same recovery accuracy as penalization methods, while naturally integrating computational considerations. An empirical analysis on a number of problems provides promising results with respect to the state of the art.
References in corpus (11)
- Rejoinder to "Least angle regression" by Efron et al
- Least Angle Regression
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Early stopping and non-parametric regression: An optimal data-dependent stopping rule
Cited by in corpus (6)
- Iterative regularization via dual diagonal descent
- Accelerated iterative regularization via dual diagonal descent
- An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration
- CORE-Deblur: Parallel MRI Reconstruction by Deblurring Using Compressed Sensing
- Convergence of inertial dynamics and proximal algorithms governed by maximally monotone operators
- Iterative regularization for convex regularizers