QuProFS: An Evolutionary Training-free Approach to Efficient Quantum Feature Map Search

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gujju, Yaswitha, Harang, Romain, Li, Chao, Shibuya, Tetsuo, Zhao, Qibin
Format:	Preprint
Published:	2025
Subjects:	Quantum Physics Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866916890277838848
author	Gujju, Yaswitha Harang, Romain Li, Chao Shibuya, Tetsuo Zhao, Qibin
author_facet	Gujju, Yaswitha Harang, Romain Li, Chao Shibuya, Tetsuo Zhao, Qibin
contents	The quest for effective quantum feature maps for data encoding presents significant challenges, particularly due to the flat training landscapes and lengthy training processes associated with parameterised quantum circuits. To address these issues, we propose an evolutionary training-free quantum architecture search (QAS) framework that employs circuit-based heuristics focused on trainability, hardware robustness, generalisation ability, expressivity, complexity, and kernel-target alignment. By ranking circuit architectures with various proxies, we reduce evaluation costs and incorporate hardware-aware circuits to enhance robustness against noise. We evaluate our approach on classification tasks (using quantum support vector machine) across diverse datasets using both artificial and quantum-generated datasets. Our approach demonstrates competitive accuracy on both simulators and real quantum hardware, surpassing state-of-the-art QAS methods in terms of sampling efficiency and achieving up to a 2x speedup in architecture search runtime.
format	Preprint
id	arxiv_https___arxiv_org_abs_2508_07104
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	QuProFS: An Evolutionary Training-free Approach to Efficient Quantum Feature Map Search Gujju, Yaswitha Harang, Romain Li, Chao Shibuya, Tetsuo Zhao, Qibin Quantum Physics Machine Learning The quest for effective quantum feature maps for data encoding presents significant challenges, particularly due to the flat training landscapes and lengthy training processes associated with parameterised quantum circuits. To address these issues, we propose an evolutionary training-free quantum architecture search (QAS) framework that employs circuit-based heuristics focused on trainability, hardware robustness, generalisation ability, expressivity, complexity, and kernel-target alignment. By ranking circuit architectures with various proxies, we reduce evaluation costs and incorporate hardware-aware circuits to enhance robustness against noise. We evaluate our approach on classification tasks (using quantum support vector machine) across diverse datasets using both artificial and quantum-generated datasets. Our approach demonstrates competitive accuracy on both simulators and real quantum hardware, surpassing state-of-the-art QAS methods in terms of sampling efficiency and achieving up to a 2x speedup in architecture search runtime.
title	QuProFS: An Evolutionary Training-free Approach to Efficient Quantum Feature Map Search
topic	Quantum Physics Machine Learning
url	https://arxiv.org/abs/2508.07104