English

Generalized Nonconvex Nonsmooth Low-Rank Minimization

Computer Vision and Pattern Recognition 2016-11-17 v1 Machine Learning Machine Learning

Abstract

As surrogate functions of L0L_0-norm, many nonconvex penalty functions have been proposed to enhance the sparse vector recovery. It is easy to extend these nonconvex penalty functions on singular values of a matrix to enhance low-rank matrix recovery. However, different from convex optimization, solving the nonconvex low-rank minimization problem is much more challenging than the nonconvex sparse minimization problem. We observe that all the existing nonconvex penalty functions are concave and monotonically increasing on [0,)[0,\infty). Thus their gradients are decreasing functions. Based on this property, we propose an Iteratively Reweighted Nuclear Norm (IRNN) algorithm to solve the nonconvex nonsmooth low-rank minimization problem. IRNN iteratively solves a Weighted Singular Value Thresholding (WSVT) problem. By setting the weight vector as the gradient of the concave penalty function, the WSVT problem has a closed form solution. In theory, we prove that IRNN decreases the objective function value monotonically, and any limit point is a stationary point. Extensive experiments on both synthetic data and real images demonstrate that IRNN enhances the low-rank matrix recovery compared with state-of-the-art convex algorithms.

Keywords

Cite

@article{arxiv.1404.7306,
  title  = {Generalized Nonconvex Nonsmooth Low-Rank Minimization},
  author = {Canyi Lu and Jinhui Tang and Shuicheng Yan and Zhouchen Lin},
  journal= {arXiv preprint arXiv:1404.7306},
  year   = {2016}
}

Comments

IEEE International Conference on Computer Vision and Pattern Recognition, 2014

R2 v1 2026-06-22T04:01:35.658Z