Optimization Online


Provable Low-Rank Tensor Recovery

Bo Huang(bh2359***at***columbia.edu)
Cun Mu(cm3052***at***columbia.edu)
John Wright(johnwright***at***ee.columbia.edu)
Donald Goldfarb(goldfarb***at***columbia.edu)

Abstract: In this paper, we rigorously study tractable models for provably recovering low-rank tensors. Unlike their matrix-based predecessors, current convex approaches for recovering low-rank tensors based on incomplete (tensor completion) and/or grossly corrupted (tensor robust principal analysis) observations still suffer from the lack of theoretical guarantees, although they have been used in various recent applications and have exhibited promising empirical performance. In this work, we attempt to fill this gap. Specifically, we propose a class of convex recovery models (including strongly convex programs) that can be proved to guarantee exact recovery under certain conditions. All parameters in our formulations can be determined beforehand based on the measurement data and thus there is no parameter tuning involved.

Keywords: Low-rank tensor recovery, tensor completion, tensor robust principal component analysis, Tucker decomposition, strongly convex programming, incoherence condition, sum of nuclear norms minimization

Category 1: Convex and Nonsmooth Optimization


Download: [PDF]

Entry Submitted: 02/26/2014
Entry Accepted: 02/26/2014
Entry Last Modified: 02/26/2014

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society