Saved in:
Bibliographic Details
Main Authors: Everink, Jasper Marijn, Dong, Yiqiu, Andersen, Martin Skovgaard
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.03461
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929487842639872
author Everink, Jasper Marijn
Dong, Yiqiu
Andersen, Martin Skovgaard
author_facet Everink, Jasper Marijn
Dong, Yiqiu
Andersen, Martin Skovgaard
contents In this work, we study the well-posedness of certain sparse regularized linear regression problems, i.e., the existence, uniqueness and continuity of the solution map with respect to the data. We focus on regularization functions that are convex piecewise linear, i.e., whose epigraph is polyhedral. This includes total variation on graphs and polyhedral constraints. We provide a geometric framework for these functions based on their connection to polyhedral sets and apply this to the study of the well-posedness of the corresponding sparse regularized linear regression problem. Particularly, we provide geometric conditions for well-posedness of the regression problem, compare these conditions to those for smooth regularization, and show the computational difficulty of verifying these conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03461
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Geometry and Well-Posedness of Sparse Regularized Linear Regression
Everink, Jasper Marijn
Dong, Yiqiu
Andersen, Martin Skovgaard
Statistics Theory
Optimization and Control
52B99, 62J05, 90C31
In this work, we study the well-posedness of certain sparse regularized linear regression problems, i.e., the existence, uniqueness and continuity of the solution map with respect to the data. We focus on regularization functions that are convex piecewise linear, i.e., whose epigraph is polyhedral. This includes total variation on graphs and polyhedral constraints. We provide a geometric framework for these functions based on their connection to polyhedral sets and apply this to the study of the well-posedness of the corresponding sparse regularized linear regression problem. Particularly, we provide geometric conditions for well-posedness of the regression problem, compare these conditions to those for smooth regularization, and show the computational difficulty of verifying these conditions.
title The Geometry and Well-Posedness of Sparse Regularized Linear Regression
topic Statistics Theory
Optimization and Control
52B99, 62J05, 90C31
url https://arxiv.org/abs/2409.03461