Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kamisoyama, Kensuke, Nagano, Lento, Terashi, Koji
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.17202
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918454487941120
author Kamisoyama, Kensuke
Nagano, Lento
Terashi, Koji
author_facet Kamisoyama, Kensuke
Nagano, Lento
Terashi, Koji
contents Various classical machine learning models, including linear regression, kernel methods, and deep neural networks, exhibit double descent, in which the test risk peaks near the interpolation threshold and then decreases in the overparameterized regime. However, this phenomenon has received less attention in the quantum setting. In this work, we investigate the double descent phenomenon in quantum kernel ridge regression (QKRR). By applying deterministic equivalents from random matrix theory (RMT), we derive an asymptotic expression for the test risk of QKRR in the high-dimensional limit. Our analysis rigorously characterizes the interpolation peak and reveals how explicit regularization can effectively suppress it. We corroborate our theoretical results with numerical simulations, demonstrating close agreement even for finite-size quantum systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17202
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Double Descent in Quantum Kernel Ridge Regression
Kamisoyama, Kensuke
Nagano, Lento
Terashi, Koji
Quantum Physics
Various classical machine learning models, including linear regression, kernel methods, and deep neural networks, exhibit double descent, in which the test risk peaks near the interpolation threshold and then decreases in the overparameterized regime. However, this phenomenon has received less attention in the quantum setting. In this work, we investigate the double descent phenomenon in quantum kernel ridge regression (QKRR). By applying deterministic equivalents from random matrix theory (RMT), we derive an asymptotic expression for the test risk of QKRR in the high-dimensional limit. Our analysis rigorously characterizes the interpolation peak and reveals how explicit regularization can effectively suppress it. We corroborate our theoretical results with numerical simulations, demonstrating close agreement even for finite-size quantum systems.
title Double Descent in Quantum Kernel Ridge Regression
topic Quantum Physics
url https://arxiv.org/abs/2604.17202