Convex Recovery of Tensors Using Nuclear Norm Penalization
| Affiliation auteurs | !!!! Error affiliation !!!! |
| Titre | Convex Recovery of Tensors Using Nuclear Norm Penalization |
| Type de publication | Conference Paper |
| Year of Publication | 2015 |
| Auteurs | Chretien S, Wei T |
| Editor | Vincent E, Yeredor A, Koldovsky Z, Tichavsky P |
| Conference Name | LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION, LVA/ICA 2015 |
| Publisher | Technicolor; Tech Univ Liberec, Fac Mechatron, Informat & Interdisciplinary Studies; Jablotron; Conexant Syst; Sony |
| Conference Location | HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY |
| ISBN Number | 978-3-319-22482-4; 978-3-319-22481-7 |
| Résumé | The subdifferential of convex functions of the singular spectrum of real matrices has been widely studied in matrix analysis, optimization and automatic control theory. Convex analysis and optimization over spaces of tensors is now gaining much interest due to its potential applications to signal processing, statistics and engineering. The goal of this paper is to present an applications to the problem of low rank tensor recovery based on linear random measurement by extending the results of Tropp [6] to the tensors setting. |
| DOI | 10.1007/978-3-319-22482-4_42 |