Towards Automated Selection of Quantum Encoding Circuits via Meta-Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tung, Dao Duy, Chuong, Nguyen Quoc, Hai, Vu Tuan, Ho, Le Bin, Tran, Lan Nguyen
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918459140472832
author Tung, Dao Duy
Chuong, Nguyen Quoc
Hai, Vu Tuan
Ho, Le Bin
Tran, Lan Nguyen
author_facet Tung, Dao Duy
Chuong, Nguyen Quoc
Hai, Vu Tuan
Ho, Le Bin
Tran, Lan Nguyen
contents In recent years, quantum kernel methods have shown promising applications on near-term quantum devices. However, selecting an appropriate encoding circuit for a given dataset requires costly evaluation of multiple candidates, formulated as a meta-learning problem. In this paper, we propose an automated recommender that utilizes the intrinsic characteristics of datasets to predict the optimal circuit without any quantum evaluation. Nine candidates are assessed alongside 24 classical complexity metrics serving as features, evaluated through two training approaches with four configurations, along with 14 machine learning models. Both approaches achieve Top-3 accuracy of up to 85.7% in identifying the best-performing encoding circuit, and demonstrate that classical data complexity metrics provide sufficient predictive signal for circuit selection.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19076
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Automated Selection of Quantum Encoding Circuits via Meta-Learning
Tung, Dao Duy
Chuong, Nguyen Quoc
Hai, Vu Tuan
Ho, Le Bin
Tran, Lan Nguyen
Quantum Physics
In recent years, quantum kernel methods have shown promising applications on near-term quantum devices. However, selecting an appropriate encoding circuit for a given dataset requires costly evaluation of multiple candidates, formulated as a meta-learning problem. In this paper, we propose an automated recommender that utilizes the intrinsic characteristics of datasets to predict the optimal circuit without any quantum evaluation. Nine candidates are assessed alongside 24 classical complexity metrics serving as features, evaluated through two training approaches with four configurations, along with 14 machine learning models. Both approaches achieve Top-3 accuracy of up to 85.7% in identifying the best-performing encoding circuit, and demonstrate that classical data complexity metrics provide sufficient predictive signal for circuit selection.
title Towards Automated Selection of Quantum Encoding Circuits via Meta-Learning
topic Quantum Physics
url https://arxiv.org/abs/2604.19076