A Super-Resolution Framework for Tensor Decomposition

DOI10.1093/IMAIAI/IAAC002MaRDI QIDQ6270906arXivWikidataFDO

Authors Qiuwei Li, Ashley Prater, Lixin Shen, Gongguo Tang

Publication date 27 February 2016

Published in arXiv

Full work available at URL https://doi.org/10.1093/IMAIAI/IAAC002

Mathematics Subject Classification ID

Factorization of matrices (15A23) Multilinear algebra, tensor calculus (15A69) Numerical mathematical programming methods (65K05)

arXiv classification

cs.ITmath.IT

Abstract: This work considers a super-resolution framework for overcomplete tensor decomposition. Specifically, we view tensor decomposition as a super-resolution problem of recovering a sum of Dirac measures on the sphere and solve it by minimizing a continuous analog of the $el{l}_1$ norm on the space of measures. The optimal value of this optimization defines the tensor nuclear norm. Similar to the separation condition in the super-resolution problem, by explicitly constructing a dual certificate, we develop incoherence conditions of the tensor factors so that they form the unique optimal solution of the continuous analog of $el{l}_1$ norm minimization. Remarkably, the derived incoherence conditions are satisfied with high probability by random tensor factors uniformly distributed on the sphere, implying global identifiability of random tensor factors.

This page was built for publication: A Super-Resolution Framework for Tensor Decomposition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6270906)