Parameter selection for nonnegative l1 matrix/tensor sparse decomposition
| dc.contributor.author | Wang, Y. | |
| dc.contributor.author | Liu, Wan-Quan | |
| dc.contributor.author | Caccetta, Louis | |
| dc.contributor.author | Zhou, Guanglu | |
| dc.date.accessioned | 2017-01-30T14:21:59Z | |
| dc.date.available | 2017-01-30T14:21:59Z | |
| dc.date.created | 2015-08-31T20:00:40Z | |
| dc.date.issued | 2015 | |
| dc.identifier.citation | Wang, Y. and Liu, W. and Caccetta, L. and Zhou, G. 2015. Parameter selection for nonnegative l1 matrix/tensor sparse decomposition. Operations Research Letters. 43: pp. 423-426. | |
| dc.identifier.uri | http://hdl.handle.net/20.500.11937/38485 | |
| dc.identifier.doi | 10.1016/j.orl.2015.06.005 | |
| dc.description.abstract |
For the nonnegative l1 matrix/tensor sparse decomposition problem, we derive a threshold bound for the parameters beyond which all the decomposition factors are zero. The obtained result provides a guideline on selection for l1 regularization parameters and extends the corresponding result on Lasso optimization problem. | |
| dc.publisher | Elsevier | |
| dc.subject | Threshold bound | |
| dc.subject | Global optimal solution | |
| dc.subject | Zero solution | |
| dc.subject | Regularization parameter | |
| dc.subject | Sparse decomposition | |
| dc.title | Parameter selection for nonnegative l1 matrix/tensor sparse decomposition | |
| dc.type | Journal Article | |
| dcterms.source.volume | 43 | |
| dcterms.source.startPage | 423 | |
| dcterms.source.endPage | 426 | |
| dcterms.source.issn | 0167-6377 | |
| dcterms.source.title | Operations Research Letters | |
| curtin.department | Department of Computing | |
| curtin.accessStatus | Fulltext not available |