# Tensor-based Multi-layer Decoupling

arXiv: https://arxiv.org/abs/2604.10858 · HTML: https://mlsanity.com/paper/2604.10858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2026.

## Built on by (most cited first, 1 of 1)

- [Robust Basis Spline Decoupling for the Compression of Transformer Models](https://mlsanity.com/paper/2605.18794/) (2026)

## Abstract (arXiv)

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.