RT Journal Article
T1 Tensorization of neural networks for improved privacy and interpretability
A1 Pareja Monturiol, José Ramón
A1 Pozas Kerstjens, Alejandro
A1 Pérez García, David
AB We present a tensorization algorithm for constructing tensor train/matrix product state (MPS) representations of functions, drawing on sketching and cross interpolation ideas. The method only requires black-box access to the target function and a small set of sample points defining the domain of interest. Thus, it is particularly well-suited for machine learning models, where the domain of interest is naturally defined by the training dataset. We show that this approach can be used to enhance the privacy and interpretability of neural network models. Specifically, we apply our decomposition to (i) obfuscate neural networks whose parameters encode patterns tied to the training data distribution, and (ii) estimate topological phases of matter that are easily accessible from the MPS representation. Additionally, we show that this tensorization can serve as an efficient initialization method for optimizing MPS in general settings, and that, for model compression, our algorithm achieves a superior trade-off between memory and time complexity compared to conventional tensorization methods of neural networks.
PB SciPost
SN 2666-9366
YR 2025
FD 2025
LK https://hdl.handle.net/20.500.14352/134937
UL https://hdl.handle.net/20.500.14352/134937
LA eng
NO Ministerio de Ciencia e Innovación
NO Comunidad de Madrid
NO Universidad Complutense de Madrid
DS Docta Complutense
RD 14 jun 2026