A condition number for the tensor rank decomposition

Abstract

The tensor rank decomposition problem consists of recovering the unique set of parameters representing a robustly identifiable low-rank tensor when the coordinate representation of the tensor is presented as input. A condition number for this problem measuring the sensitivity of the parameters to an infinitesimal change to the tensor is introduced and analyzed. It is demonstrated that the absolute condition number coincides with the inverse of the least singular value of Terracini's matrix. Several basic properties of this condition number are investigated.

45 pages, 4 figures

References in corpus (6)

• Identifiability of parameters in latent structure models with many observed variables
• An algorithm for generic and low-rank specific identifiability of complex tensors
• Generic uniqueness conditions for the canonical polyadic decomposition and INDSCAL
• Effective criteria for specific identifiability of tensors and forms
• The condition number of join decompositions
• Homotopy techniques for tensor decomposition and perfect identifiability

Cited by in corpus (10)

• The condition number of join decompositions
• A Riemannian Trust Region Method for the Canonical Tensor Rank Approximation Problem
• Pencil-based algorithms for tensor rank decomposition are not stable
• Accelerating Block Coordinate Descent for Nonnegative Tensor Factorization
• On Recoverability of Randomly Compressed Tensors with Low CP Rank
• On the average condition number of tensor rank decompositions
• The condition number of many tensor decompositions is invariant under Tucker compression
• Perturbation Analysis for Matrix Joint Block Diagonalization
• Tensor decompositions and algorithms, with applications to tensor learning
• Which constraints of a numerical problem cause ill-conditioning?