Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nishikawa, Kohei, Shimizu, Koki, Hashiguchi, Hiroki
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.12911
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913017652838400
author Nishikawa, Kohei
Shimizu, Koki
Hashiguchi, Hiroki
author_facet Nishikawa, Kohei
Shimizu, Koki
Hashiguchi, Hiroki
contents This study evaluates thresholds for removing singular values from singular value decomposition-based low-rank approximations of deep neural network weight matrices. Each weight matrix is modeled as the sum of signal and noise matrices. The low-rank approximation is obtained by removing noise-related singular values using a threshold based on random matrix theory. To assess the adequacy of this threshold, we propose an evaluation metric based on the cosine similarity between the singular vectors of the signal and original weight matrices. The proposed metric is used in numerical experiments to compare two threshold estimation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12911
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Singular Value Thresholds for DNN Weight Matrices based on Random Matrix Theory
Nishikawa, Kohei
Shimizu, Koki
Hashiguchi, Hiroki
Machine Learning
This study evaluates thresholds for removing singular values from singular value decomposition-based low-rank approximations of deep neural network weight matrices. Each weight matrix is modeled as the sum of signal and noise matrices. The low-rank approximation is obtained by removing noise-related singular values using a threshold based on random matrix theory. To assess the adequacy of this threshold, we propose an evaluation metric based on the cosine similarity between the singular vectors of the signal and original weight matrices. The proposed metric is used in numerical experiments to compare two threshold estimation methods.
title Evaluating Singular Value Thresholds for DNN Weight Matrices based on Random Matrix Theory
topic Machine Learning
url https://arxiv.org/abs/2512.12911