ℓ1-2 Regularization for Sparse Optimization: Consistency and Global Convergence

Hu, Yaohua

doi:10.1287/moor.2025.1095

Return

ℓ1-2 Regularization for Sparse Optimization: Consistency and Global Convergence

2026-01-01

PRE

Hu, Yaohua *

Hao Wang

Yang, Xiaoqi

DOI：10.1287/moor.2025.1095

Original

Original request for help

Save

Abstract

En 中文

The & ell;1-2 regularization method has a strong sparsity-promoting capability in approaching sparse solutions of linear inverse problems and gains successful applications in various mathematics disciplines and applied science fields. This paper aims to investigate the consistency theory and global convergent algorithms for the & ell;1-2 regularization problem. In the theoretical aspect, we introduce a notion of restricted eigenvalue condition relative to the & ell;1-2 penalty and employ it to establish an oracle property and a recovery bound for the global solution of the & ell;1-2 regularization problem. In the algorithmic aspect, we propose two types of iterative thresholding algorithms with the truncation technique and the continuation technique, respectively, to solve the & ell;1-2 regularization problem. Moreover, under the assumption of the well-known restricted isometry property, we establish the convergence of the proposed algorithms to the ground true sparse solution within a tolerance relevant to the noise level and the recovery bound. Preliminary numerical results verify our theoretical convergence results in showing that the proposed algorithms can approach the ground true sparse solution and significantly enhance the sparsity recovery capability, compared with the popular sparse optimization algorithms in the literature.

Keywords:

sparse optimization

l(1-2) regularization

consistency theory

iterative thresholding algorithm

global convergence

ground true solution