Kernel Alignment for Quantum Support Vector Machines Using Genetic Algorithms
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913151343132672 |
|---|---|
| author | Creevey, Floyd M. Heredge, Jamie A. Sevior, Martin E. Hollenberg, Lloyd C. L. |
| author_facet | Creevey, Floyd M. Heredge, Jamie A. Sevior, Martin E. Hollenberg, Lloyd C. L. |
| contents | The data encoding circuits used in quantum support vector machine (QSVM) kernels play a crucial role in their classification accuracy. However, manually designing these circuits poses significant challenges in terms of time and performance. To address this, we leverage the GASP (Genetic Algorithm for State Preparation) framework for gate sequence selection in QSVM kernel circuits. We explore supervised and unsupervised kernel loss functions' impact on encoding circuit optimisation and evaluate them on diverse datasets for binary and multiple-class scenarios. Benchmarking against classical and quantum kernels reveals GA-generated circuits matching or surpassing standard techniques. We analyse the relationship between test accuracy and quantum kernel entropy, with results indicating a positive correlation. Our automated framework reduces trial and error, and enables improved QSVM based machine learning performance for finance, healthcare, and materials science applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_01562 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Kernel Alignment for Quantum Support Vector Machines Using Genetic Algorithms Creevey, Floyd M. Heredge, Jamie A. Sevior, Martin E. Hollenberg, Lloyd C. L. Quantum Physics The data encoding circuits used in quantum support vector machine (QSVM) kernels play a crucial role in their classification accuracy. However, manually designing these circuits poses significant challenges in terms of time and performance. To address this, we leverage the GASP (Genetic Algorithm for State Preparation) framework for gate sequence selection in QSVM kernel circuits. We explore supervised and unsupervised kernel loss functions' impact on encoding circuit optimisation and evaluate them on diverse datasets for binary and multiple-class scenarios. Benchmarking against classical and quantum kernels reveals GA-generated circuits matching or surpassing standard techniques. We analyse the relationship between test accuracy and quantum kernel entropy, with results indicating a positive correlation. Our automated framework reduces trial and error, and enables improved QSVM based machine learning performance for finance, healthcare, and materials science applications. |
| title | Kernel Alignment for Quantum Support Vector Machines Using Genetic Algorithms |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2312.01562 |