Tensor-based Multi-layer Decoupling

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: De Jonghe, Joppe, Usevich, Konstantin, Dreesen, Philippe, Ishteva, Mariya
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908957699735552
author De Jonghe, Joppe
Usevich, Konstantin
Dreesen, Philippe
Ishteva, Mariya
author_facet De Jonghe, Joppe
Usevich, Konstantin
Dreesen, Philippe
Ishteva, Mariya
contents The decoupling of multivariate functions is a powerful modeling paradigm for learning multivariate input-output relations from data. For the single-layer case, established CPD-based methods are available, but the multi-layer case remained largely unexplored. This work introduces a tensor-based framework for multi-layer decoupling, which is based on ParaTuck-type tensor decompositions and constrained optimization. We provide theoretical justification behind the considered tensor decompositions and parameterizations. Furthermore, we formulate a structured coupled matrix-tensor factorization that incorporates both Jacobian and function evaluations, together with a bilevel optimization approach for adaptively balancing first- and zeroth-order information. The feasibility of the proposed methodology is illustrated on synthetic systems, a nonlinear system identification benchmark and neural network compression.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10858
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tensor-based Multi-layer Decoupling
De Jonghe, Joppe
Usevich, Konstantin
Dreesen, Philippe
Ishteva, Mariya
Systems and Control
The decoupling of multivariate functions is a powerful modeling paradigm for learning multivariate input-output relations from data. For the single-layer case, established CPD-based methods are available, but the multi-layer case remained largely unexplored. This work introduces a tensor-based framework for multi-layer decoupling, which is based on ParaTuck-type tensor decompositions and constrained optimization. We provide theoretical justification behind the considered tensor decompositions and parameterizations. Furthermore, we formulate a structured coupled matrix-tensor factorization that incorporates both Jacobian and function evaluations, together with a bilevel optimization approach for adaptively balancing first- and zeroth-order information. The feasibility of the proposed methodology is illustrated on synthetic systems, a nonlinear system identification benchmark and neural network compression.
title Tensor-based Multi-layer Decoupling
topic Systems and Control
url https://arxiv.org/abs/2604.10858