The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices

<p dir="ltr">Quantum neural networks (QNNs) are often challenged with the problem of flat cost function landscapes during training, known as barren plateaus (BP). A solution to potentially overcome the problem of the BP has recently been proposed by Cerezo et al In this solution, it...

Full description

Saved in:
Bibliographic Details
Main Author: Muhammad Kashif (3923483) (author)
Other Authors: Saif Al-Kuwari (16904610) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513509217271808
author Muhammad Kashif (3923483)
author2 Saif Al-Kuwari (16904610)
author2_role author
author_facet Muhammad Kashif (3923483)
Saif Al-Kuwari (16904610)
author_role author
dc.creator.none.fl_str_mv Muhammad Kashif (3923483)
Saif Al-Kuwari (16904610)
dc.date.none.fl_str_mv 2023-01-20T09:00:00Z
dc.identifier.none.fl_str_mv 10.1088/2632-2153/acb12f
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/The_impact_of_cost_function_globality_and_locality_in_hybrid_quantum_neural_networks_on_NISQ_devices/26535445
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Machine learning
Physical sciences
Quantum physics
quantum machine learning
quantum neural networks
barren plateaus
qubit measurements
cost function
dc.title.none.fl_str_mv The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Quantum neural networks (QNNs) are often challenged with the problem of flat cost function landscapes during training, known as barren plateaus (BP). A solution to potentially overcome the problem of the BP has recently been proposed by Cerezo et al In this solution, it is shown that, for an arbitrary deep quantum layer(s) in QNNs, a global cost function (all qubits measured in an n-qubit system) will always experience BP, whereas a local cost function (single qubit measured in an n-qubit system) can help to alleviate the problem of BP to a certain depth ( )). In this paper, we empirically analyze the locality and globality of the cost function in hybrid quantum neural networks. We consider two application scenarios namely, binary and multi-class classification, and show that for multiclass classification, the local cost function setting does not follow the claims of Cerezo et al; that is, the local cost function does not result in an extended quantum layer’s depth. We also show that for multiclass classification, the overall performance in terms of accuracy for the global cost function setting is significantly higher than the local cost function setting. On the other hand, for binary classification, our results show that the local cost function setting follows the claims of Cerezo et al, and results in an extended depth of quantum layers. However, the global cost function setting still performs slightly better than the local cost function.</p><h2>Other Information</h2><p dir="ltr">Published in: Machine Learning: Science and Technology<br>License: <a href="http://creativecommons.org/licenses/by/4.0" target="_blank">http://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1088/2632-2153/acb12f" target="_blank">https://dx.doi.org/10.1088/2632-2153/acb12f</a></p>
eu_rights_str_mv openAccess
id Manara2_6fd12887b71e2b551e1307fca75c70d0
identifier_str_mv 10.1088/2632-2153/acb12f
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26535445
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devicesMuhammad Kashif (3923483)Saif Al-Kuwari (16904610)Information and computing sciencesMachine learningPhysical sciencesQuantum physicsquantum machine learningquantum neural networksbarren plateausqubit measurementscost function<p dir="ltr">Quantum neural networks (QNNs) are often challenged with the problem of flat cost function landscapes during training, known as barren plateaus (BP). A solution to potentially overcome the problem of the BP has recently been proposed by Cerezo et al In this solution, it is shown that, for an arbitrary deep quantum layer(s) in QNNs, a global cost function (all qubits measured in an n-qubit system) will always experience BP, whereas a local cost function (single qubit measured in an n-qubit system) can help to alleviate the problem of BP to a certain depth ( )). In this paper, we empirically analyze the locality and globality of the cost function in hybrid quantum neural networks. We consider two application scenarios namely, binary and multi-class classification, and show that for multiclass classification, the local cost function setting does not follow the claims of Cerezo et al; that is, the local cost function does not result in an extended quantum layer’s depth. We also show that for multiclass classification, the overall performance in terms of accuracy for the global cost function setting is significantly higher than the local cost function setting. On the other hand, for binary classification, our results show that the local cost function setting follows the claims of Cerezo et al, and results in an extended depth of quantum layers. However, the global cost function setting still performs slightly better than the local cost function.</p><h2>Other Information</h2><p dir="ltr">Published in: Machine Learning: Science and Technology<br>License: <a href="http://creativecommons.org/licenses/by/4.0" target="_blank">http://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1088/2632-2153/acb12f" target="_blank">https://dx.doi.org/10.1088/2632-2153/acb12f</a></p>2023-01-20T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1088/2632-2153/acb12fhttps://figshare.com/articles/journal_contribution/The_impact_of_cost_function_globality_and_locality_in_hybrid_quantum_neural_networks_on_NISQ_devices/26535445CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/265354452023-01-20T09:00:00Z
spellingShingle The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
Muhammad Kashif (3923483)
Information and computing sciences
Machine learning
Physical sciences
Quantum physics
quantum machine learning
quantum neural networks
barren plateaus
qubit measurements
cost function
status_str publishedVersion
title The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
title_full The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
title_fullStr The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
title_full_unstemmed The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
title_short The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
title_sort The impact of cost function globality and locality in hybrid quantum neural networks on NISQ devices
topic Information and computing sciences
Machine learning
Physical sciences
Quantum physics
quantum machine learning
quantum neural networks
barren plateaus
qubit measurements
cost function