Abstract | ||
---|---|---|
We propose a robust approach to recovering the jointly-sparse signals in the presence of outliers. We formulate the recovering task as a minimization problem involving three terms: (i) the minimax concave (MC) loss function, (ii) the MC penalty function, and (iii) the squared Frobenius norm. The MC-based loss and penalty functions enhance robustness and group sparsity, respectively, while the squared Frobenius norm induces the convexity. The problem is solved, via reformulation, by the primal-dual splitting method, for which the convergence condition is derived. Numerical examples show that the proposed approach enjoys remarkable outlier robustness. |
Year | DOI | Venue |
---|---|---|
2020 | 10.23919/Eusipco47968.2020.9287635 | 28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020) |
Keywords | DocType | ISSN |
robustness, minimax concave function, jointly-sparse signals, multiple measurement vector problem, feature selection | Conference | 2076-1465 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kyohei Suzuki | 1 | 0 | 0.34 |
Masahiro Yukawa | 2 | 272 | 30.44 |