Convergence rate analysis of proximal iteratively reweighted ℓ 1 methods for ℓ p regularization problems

Hao Wang, Hao Zeng, Jiashan Wang

Abstract: In this paper, we focus on the local convergence rate analysis of the proximal iteratively reweighted $$\ell _1$$ ℓ 1 algorithms for solving $$\ell _p$$ ℓ p regularization problems, which are widely applied for inducing sparse solutions. We show that if the Kurdyka–Łojasiewicz property is satisfied, the algorithm converges to a unique first-order stationary point; furthermore, the algorithm has local linear convergence or local sublinear convergence. The theoretical results we derived are much stronger than the existing results for iteratively reweighted $$\ell _1$$ ℓ 1 algorithms.