Journal
COMPUTATIONAL OPTIMIZATION AND APPLICATIONS
Volume 79, Issue 2, Pages 273-300Publisher
SPRINGER
DOI: 10.1007/s10589-021-00276-5
Keywords
Rank minimization; Matrix completion; Nonconvex regularizers; Semidefinite programming
Ask authors/readers for more resources
This study introduces an algorithm based on nuclear norm and low rank factorization for solving the rank minimization problem, which has less estimation bias and can reduce the effect of noise on measurements compared to convex relaxations. By iteratively reweighted nuclear norm schemes, it efficiently solves the rank minimization problem for large matrices.
Rank minimization is of interest in machine learning applications such as recommender systems and robust principal component analysis. Minimizing the convex relaxation to the rank minimization problem, the nuclear norm, is an effective technique to solve the problem with strong performance guarantees. However, nonconvex relaxations have less estimation bias than the nuclear norm and can more accurately reduce the effect of noise on the measurements. We develop efficient algorithms based on iteratively reweighted nuclear norm schemes, while also utilizing the low rank factorization for semidefinite programs put forth by Burer and Monteiro. We prove convergence and computationally show the advantages over convex relaxations and alternating minimization methods. Additionally, the computational complexity of each iteration of our algorithm is on par with other state of the art algorithms, allowing us to quickly find solutions to the rank minimization problem for large matrices.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available