Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization

Wang, Y; Qi, B; Ferrie, C; Dong, D

Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization

Wang, Y Qi, B Ferrie, C

Dong, D

Permalink

Publisher:: AMER PHYSICAL SOC
Publication Type:: Journal Article
Citation:: Physical Review Applied, 2024, 22, (5)
Issue Date:: 2024-11-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Download Accepted versionAdobe PDF (1.98 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, Y
dc.contributor.author	Qi, B
dc.contributor.author	Ferrie, C https://orcid.org/0000-0003-2736-9943
dc.contributor.author	Dong, D
dc.date.accessioned	2025-01-06T03:07:33Z
dc.date.available	2024-10-16
dc.date.available	2025-01-06T03:07:33Z
dc.date.issued	2024-11-01
dc.identifier.citation	Physical Review Applied, 2024, 22, (5)
dc.identifier.issn	2331-7019
dc.identifier.issn	2331-7019
dc.identifier.uri	http://hdl.handle.net/10453/183012
dc.description.abstract	Parameterized quantum circuits (PQCs) have been widely used as a machine learning model to explore the potential of achieving quantum advantages for various tasks. However, training PQCs is notoriously challenging owing to the phenomenon of plateaus and/or the existence of (exponentially) many spurious local minima. To enhance trainability, in this work we propose an efficient parameter initialization strategy with theoretical guarantees. We prove that, by reducing the initial domain of each parameter inversely proportional to the square root of the circuit depth, the magnitude of the cost gradient decays at most polynomially with respect to the qubit count and circuit depth. Our theoretical results are substantiated through numerical simulations of variational quantum eigensolver tasks. Moreover, we demonstrate that the reduced-domain initialization strategy can protect specific quantum neural networks from exponentially many spurious local minima. Our results highlight the significance of an appropriate parameter initialization strategy, offering insights to enhance the trainability and convergence of variational quantum algorithms.
dc.language	English
dc.publisher	AMER PHYSICAL SOC
dc.relation.ispartof	Physical Review Applied
dc.relation.isbasedon	10.1103/PhysRevApplied.22.054005
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	© American Physical Society (APS) Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization. Physical Review Applied 22, 5 (2024) 10.1103/PhysRevApplied.22.054005
dc.subject	02 Physical Sciences, 09 Engineering
dc.subject.classification	40 Engineering
dc.subject.classification	51 Physical sciences
dc.title	Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization
dc.type	Journal Article
utslib.citation.volume	22
utslib.for	02 Physical Sciences
utslib.for	09 Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Centre for Quantum Software and Information (QSI)
utslib.copyright.status	open_access	*
dc.date.updated	2025-01-06T03:07:32Z
pubs.issue	5
pubs.publication-status	Published
pubs.volume	22
utslib.citation.issue	5

Abstract:

Parameterized quantum circuits (PQCs) have been widely used as a machine learning model to explore the potential of achieving quantum advantages for various tasks. However, training PQCs is notoriously challenging owing to the phenomenon of plateaus and/or the existence of (exponentially) many spurious local minima. To enhance trainability, in this work we propose an efficient parameter initialization strategy with theoretical guarantees. We prove that, by reducing the initial domain of each parameter inversely proportional to the square root of the circuit depth, the magnitude of the cost gradient decays at most polynomially with respect to the qubit count and circuit depth. Our theoretical results are substantiated through numerical simulations of variational quantum eigensolver tasks. Moreover, we demonstrate that the reduced-domain initialization strategy can protect specific quantum neural networks from exponentially many spurious local minima. Our results highlight the significance of an appropriate parameter initialization strategy, offering insights to enhance the trainability and convergence of variational quantum algorithms.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/183012