Saved in:
Bibliographic Details
Main Authors: Kimura, Fumito, Ohkubo, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.06732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910112092782592
author Kimura, Fumito
Ohkubo, Jun
author_facet Kimura, Fumito
Ohkubo, Jun
contents Recent developments in hardware, such as photonic integrated circuits and optical devices, are driving demand for research on constructing machine learning architectures tailored for linear operations. Hence, it is valuable to explore methods for constructing learning machines with only linear operations after simple nonlinear preprocessing. In this study, we propose a framework to extract a linearized model from a pre-trained neural network for classification tasks by integrating Koopman operator theory with knowledge distillation. Numerical demonstrations on the MNIST and the Fashion-MNIST datasets reveal that the proposed model consistently outperforms the conventional least-squares-based Koopman approximation in both classification accuracy and numerical stability.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06732
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Extraction of linearized models from pre-trained networks via knowledge distillation
Kimura, Fumito
Ohkubo, Jun
Machine Learning
Recent developments in hardware, such as photonic integrated circuits and optical devices, are driving demand for research on constructing machine learning architectures tailored for linear operations. Hence, it is valuable to explore methods for constructing learning machines with only linear operations after simple nonlinear preprocessing. In this study, we propose a framework to extract a linearized model from a pre-trained neural network for classification tasks by integrating Koopman operator theory with knowledge distillation. Numerical demonstrations on the MNIST and the Fashion-MNIST datasets reveal that the proposed model consistently outperforms the conventional least-squares-based Koopman approximation in both classification accuracy and numerical stability.
title Extraction of linearized models from pre-trained networks via knowledge distillation
topic Machine Learning
url https://arxiv.org/abs/2604.06732