Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

On Adaptive PARAFAC Decomposition of Three-Way Tensors

Abstract : We propose a fast adaptive PARAFAC algorithm for a class of third-order tensors which have one dimension growing linearly with time. The proposed method is based on alternating least squares approach used in conjunction with a Newton-type optimization technique. By exploiting the Khatri-Rao product and the reduced rank structure at each time instant, our algorithm has the advantages of both linear complexity and superior convergence performance. A modified version of the algorithm is also proposed to tackle the nonnegative adaptive PARAFAC problem. Parallel implementation issues and algorithm performance are finally investigated. The latter is achieved through simulation comparison with the state-of-the-art algorithms to better highlight the effectiveness of the proposed method.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-01295020
Contributor : Viet-Dung Nguyen <>
Submitted on : Wednesday, March 30, 2016 - 11:34:01 AM
Last modification on : Tuesday, June 1, 2021 - 10:00:04 AM
Long-term archiving on: : Monday, November 14, 2016 - 9:07:03 AM

File

SOAPv1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01295020, version 1

Collections

Citation

Viet-Dung Nguyen, Karim Abed-Meraim, Nguyen Linh-Trung. On Adaptive PARAFAC Decomposition of Three-Way Tensors. 2016. ⟨hal-01295020⟩

Share

Metrics

Record views

412

Files downloads

759