English

Structured Sparsity via Alternating Direction Methods

Optimization and Control 2014-02-11 v2 Artificial Intelligence Machine Learning

Abstract

We consider a class of sparse learning problems in high dimensional feature space regularized by a structured sparsity-inducing norm which incorporates prior knowledge of the group structure of the features. Such problems often pose a considerable challenge to optimization algorithms due to the non-smoothness and non-separability of the regularization term. In this paper, we focus on two commonly adopted sparsity-inducing regularization terms, the overlapping Group Lasso penalty l1/l2l_1/l_2-norm and the l1/ll_1/l_\infty-norm. We propose a unified framework based on the augmented Lagrangian method, under which problems with both types of regularization and their variants can be efficiently solved. As the core building-block of this framework, we develop new algorithms using an alternating partial-linearization/splitting technique, and we prove that the accelerated versions of these algorithms require O(1ϵ)O(\frac{1}{\sqrt{\epsilon}}) iterations to obtain an ϵ\epsilon-optimal solution. To demonstrate the efficiency and relevance of our algorithms, we test them on a collection of data sets and apply them to two real-world problems to compare the relative merits of the two norms.

Keywords

Cite

@article{arxiv.1105.0728,
  title  = {Structured Sparsity via Alternating Direction Methods},
  author = {Zhiwei Qin and Donald Goldfarb},
  journal= {arXiv preprint arXiv:1105.0728},
  year   = {2014}
}
R2 v1 2026-06-21T18:02:30.847Z