Title :
Threshold selection for noisy matrix completion
Author_Institution :
Sch. of Electr. Eng. & Telecommun., Univ. of New South Wales, Sydney, NSW, Australia
Abstract :
While noise free matrix completion has a considerable history recent interest has centered on a noisy version of the problem. We consider a nuclear norm penalised least squares formulation. And by applying the SURE method, we develop for the first time, an automatic procedure for selecting the penalty parameter. We illustrate its use with some simulation results.
Keywords :
filtering theory; least squares approximations; matrix algebra; SURE method; collaborative filtering; noise free matrix completion; nuclear norm penalised least squares formulation; threshold selection; Equations; Inverse problems; Noise; Noise measurement; Optimization; Signal processing algorithms; Tuning; denoising; matrix completion; model selection;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6638934
