Name
Abstract | ||
|---|---|---|
Recently, solving rank minimization problems by leveraging nonconvex relaxations has received significant attention. Some theoretical analyses demonstrate that it can provide a better approximation of original problems than convex relaxations. However, designing an effective algorithm to solve nonconvex optimization problems remains a big challenge. In this paper, we propose an Iterative Shrinkage-Thresholding and Reweighted Algorithm (ISTRA) to solve rank minimization problems using the nonconvex weighted nuclear norm as a low rank regularizer. We prove theoretically that under certain assumptions our method achieves a high-quality local optimal solution efficiently. Experimental results on synthetic and real data show that the proposed ISTRA algorithm outperforms state-of-the-art methods in both accuracy and efficiency. |
Year | Venue | Keywords |
|---|---|---|
2015 | PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | optimization |
Field | DocType | Citations |
Mathematical optimization,Matrix completion,Computer science,Matrix norm,Regular polygon,Optimization problem,Rank minimization | Conference | 5 |
PageRank | References | Authors |
0.41 | 8 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaowei Zhong | 1 | 24 | 1.30 |
| Linli Xu | 2 | 790 | 42.51 |
| Yitan Li | 3 | 32 | 3.11 |
| Zhiyuan Liu | 4 | 5 | 0.41 |
| Enhong Chen | 5 | 2106 | 165.57 |