A Nonconvex Approach for Structured Sparse Learning

TL;DR

This paper introduces a nonconvex $\

Contribution

It proposes a nonconvex $\\ell_q$-analysis approach for structured sparse learning with weaker recovery conditions and a new iterative algorithm.

Findings

Weaker conditions for exact recovery in noiseless cases.

Tighter error bounds in noisy scenarios.

Outperforms convex methods and state-of-the-art algorithms in experiments.

Abstract

Sparse learning is an important topic in many areas such as machine learning, statistical estimation, signal processing, etc. Recently, there emerges a growing interest on structured sparse learning. In this paper we focus on the $\ell_q$-analysis optimization problem for structured sparse learning ($0< q \leq 1$). Compared to previous work, we establish weaker conditions for exact recovery in noiseless case and a tighter non-asymptotic upper bound of estimate error in noisy case. We further prove that the nonconvex $\ell_q$-analysis optimization can do recovery with a lower sample complexity and in a wider range of cosparsity than its convex counterpart. In addition, we develop an iteratively reweighted method to solve the optimization problem under the variational framework. Theoretical analysis shows that our method is capable of pursuing a local minima close to the global minima. Also, empirical results of preliminary computational experiments illustrate that our nonconvex method outperforms both its convex counterpart and other state-of-the-art methods.