Low rank tensor recovery via iterative hard thresholding

—We study recovery of low-rank tensors from a small number of measurements. A version of the iterative hard thresholding algorithm (TIHT) for the higher order singular value decomposition (HOSVD) is introduced. As a first step towards the analysis of the algorithm, we define a corresponding tensor restricted isometry property (HOSVD-TRIP) and show that Gaussian and Bernoulli random measurement ensembles satisfy it with high probability.

• Type: Journal
• Year: 2016
• Where: CORR
• Authors: Holger Rauhut, Reinhold Schneider, Zeljka Stojanac
• Keywords: CORR 2016, Education