Two-layer decoupling of multivariate polynomials with coupled ParaTuck and CP decompositions - ANR - Agence nationale de la recherche Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Two-layer decoupling of multivariate polynomials with coupled ParaTuck and CP decompositions

Résumé

In this paper, we propose a new method for multivariate function approximation that generalized the classical decoupling problem. In the context of neural network, this can be seen as a two-layer feedforward network learning problem. In this work, we make use of both first and second-order information of the original function, modeled through ParaTuck and canonical polyadic (CP) decompositions, respectively. ParaTuck decomposition alone is not sufficient due to lack of reliable algorithms for ParaTuck decomposition. Our approach is a methodological work that demonstrates how the ParaTuck and CP decompositions can be combined in a coupled manner to achieve function decoupling according to the new model. Numerical simulations show the effectiveness of the proposed method on a simple synthetic example, demonstrating its ability to approximate multivariate functions accurately.
Fichier principal
Vignette du fichier
paratuck-long-version.pdf (454.19 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03968630 , version 1 (01-02-2023)
hal-03968630 , version 2 (10-03-2023)

Identifiants

  • HAL Id : hal-03968630 , version 2

Citer

Konstantin Usevich, Yassine Zniyed, Mariya Ishteva, Philippe Dreesen, André L F de Almeida. Two-layer decoupling of multivariate polynomials with coupled ParaTuck and CP decompositions. 2023. ⟨hal-03968630v2⟩
131 Consultations
136 Téléchargements

Partager

Gmail Facebook X LinkedIn More