Image classification with rotation-invariant variational quantum circuits
Variational quantum algorithms are gaining attention as an early application of noisy intermediate-scale quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of barren plateaus, present in the optimization of variational parameters. Adding geometric inductiv...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Physical Society
2025-01-01
|
| Series: | Physical Review Research |
| Online Access: | http://doi.org/10.1103/PhysRevResearch.7.013082 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591157642657792 |
|---|---|
| author | Paul San Sebastian Sein Mikel Cañizo Román Orús |
| author_facet | Paul San Sebastian Sein Mikel Cañizo Román Orús |
| author_sort | Paul San Sebastian Sein |
| collection | DOAJ |
| description | Variational quantum algorithms are gaining attention as an early application of noisy intermediate-scale quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of barren plateaus, present in the optimization of variational parameters. Adding geometric inductive bias to the quantum models has been proposed as a potential solution to mitigate this problem, leading to a new field called geometric quantum machine learning. In this work, an equivariant architecture for variational quantum classifiers is introduced to create a label-invariant model for image classification with C_{4} rotational label symmetry. The equivariant circuit is benchmarked against two different architectures, and it is experimentally observed that the geometric approach boosts the model's performance. Finally, a classical equivariant convolution operation is proposed to extend the quantum model for the processing of larger images, employing the resources available in NISQ devices. |
| format | Article |
| id | doaj-art-3ce1d276c0c64f83ab3f1ebb739aa4f6 |
| institution | Kabale University |
| issn | 2643-1564 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | American Physical Society |
| record_format | Article |
| series | Physical Review Research |
| spelling | doaj-art-3ce1d276c0c64f83ab3f1ebb739aa4f62025-01-22T16:02:38ZengAmerican Physical SocietyPhysical Review Research2643-15642025-01-017101308210.1103/PhysRevResearch.7.013082Image classification with rotation-invariant variational quantum circuitsPaul San Sebastian SeinMikel CañizoRomán OrúsVariational quantum algorithms are gaining attention as an early application of noisy intermediate-scale quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of barren plateaus, present in the optimization of variational parameters. Adding geometric inductive bias to the quantum models has been proposed as a potential solution to mitigate this problem, leading to a new field called geometric quantum machine learning. In this work, an equivariant architecture for variational quantum classifiers is introduced to create a label-invariant model for image classification with C_{4} rotational label symmetry. The equivariant circuit is benchmarked against two different architectures, and it is experimentally observed that the geometric approach boosts the model's performance. Finally, a classical equivariant convolution operation is proposed to extend the quantum model for the processing of larger images, employing the resources available in NISQ devices.http://doi.org/10.1103/PhysRevResearch.7.013082 |
| spellingShingle | Paul San Sebastian Sein Mikel Cañizo Román Orús Image classification with rotation-invariant variational quantum circuits Physical Review Research |
| title | Image classification with rotation-invariant variational quantum circuits |
| title_full | Image classification with rotation-invariant variational quantum circuits |
| title_fullStr | Image classification with rotation-invariant variational quantum circuits |
| title_full_unstemmed | Image classification with rotation-invariant variational quantum circuits |
| title_short | Image classification with rotation-invariant variational quantum circuits |
| title_sort | image classification with rotation invariant variational quantum circuits |
| url | http://doi.org/10.1103/PhysRevResearch.7.013082 |
| work_keys_str_mv | AT paulsansebastiansein imageclassificationwithrotationinvariantvariationalquantumcircuits AT mikelcanizo imageclassificationwithrotationinvariantvariationalquantumcircuits AT romanorus imageclassificationwithrotationinvariantvariationalquantumcircuits |