Performances estimation for tensor CP decomposition with structured factors

Abstract : The Canonical Polyadic tensor decomposition (CPD), also known as Candecomp/Parafac, is very useful in numerous scientific disciplines. Structured CPDs, i.e. with Toeplitz, circulant, or Hankel factor matrices, are often encountered in signal processing applications. As subsequently pointed out, specialized algorithms were recently proposed for estimating the deterministic parameters of structured CP decompositions. A closed-form expression of the Cramér-Rao bound (CRB) is derived, related to the problem of estimating CPD parameters, when the observed tensor is corrupted with an additive circular i.i.d. Gaussian noise. This CRB is provided for arbitrary ten-sor rank and sizes. Finally, the proposed CRB expression is used to asses the statistical efficiency of the existing algorithms by means of simulation results in the cases of third-order tensors having three cir-culant factors on one hand, and an Hankel factor on the other hand.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01072538
Contributor : Remy Boyer <>
Submitted on : Tuesday, August 25, 2015 - 1:04:10 PM
Last modification on : Wednesday, May 29, 2019 - 5:16:02 PM
Long-term archiving on : Thursday, November 26, 2015 - 1:47:50 PM

File

20150211100229_453385_3280.pdf
Files produced by the author(s)

Identifiers

Citation

Maxime Boizard, Remy Boyer, Gérard Favier, Jérémy Cohen, Pierre Comon. Performances estimation for tensor CP decomposition with structured factors. 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), Apr 2015, Brisbane, Australia. pp.3482-3486, ⟨10.1109/icassp.2015.7178618 ⟩. ⟨hal-01072538v2⟩

Share

Metrics

Record views

1381

Files downloads

264