Reweighted nuclear norm regularization: A SPARSEVA approach
From MaRDI portal
Publication:6263789
arXiv1507.05718MaRDI QIDQ6263789FDOQ6263789
James S. Welsh, Huong Giang Ha, Cristian R. Rojas, Niclas Blomberg, B. Wahlberg
Publication date: 21 July 2015
Abstract: The aim of this paper is to develop a method to estimate high order FIR and ARX models using least squares with re-weighted nuclear norm regularization. Typically, the choice of the tuning parameter in the reweighting scheme is computationally expensive, hence we propose the use of the SPARSEVA (SPARSe Estimation based on a VAlidation criterion) framework to overcome this problem. Furthermore, we suggest the use of the prediction error criterion (PEC) to select the tuning parameter in the SPARSEVA algorithm. Numerical examples demonstrate the veracity of this method which has close ties with the traditional technique of cross validation, but using much less computations.
This page was built for publication: Reweighted nuclear norm regularization: A SPARSEVA approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6263789)
