Abstract | ||
---|---|---|
Conventional approaches to matrix completion are sensitive to outliers and impulsive noise. This paper develops robust and computationally efficient M-estimation based matrix completion algorithms. By appropriately arranging the observed entries, and then applying alternating minimization, the robust matrix completion problem is converted into a set of regression M-estimation problems. Making use of differentiable loss functions, the proposed algorithm overcomes a weakness of the l(p)-loss (9 <= 1), which easily gets stuck in an inferior point. We prove that our algorithm converges to a stationary point of the nonconvex problem. Huber's joint M-estimate of regression and scale can be used as a robust starting point for Tukey's redescending M-estimator of regression based on an auxiliary scale. Numerical experiments on synthetic and real-world data demonstrate the superiority to state-of-the-art approaches. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICASSP.2019.8682657 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Low-rank factorization, matrix completion, M-estimation, robust statistics, image inpainting | Mathematical optimization,Noise measurement,Matrix completion,Computer science,Signal-to-noise ratio,Outlier,Algorithm,Differentiable function,Stationary point,Minification,Sparse matrix | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Muma | 1 | 144 | 19.51 |
wenjun zeng | 2 | 2029 | 220.14 |
Abdelhak M. Zoubir | 3 | 1036 | 148.03 |