Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915235704602624 |
|---|---|
| author | Kölle, Michael Feist, Alexander Stein, Jonas Wölckert, Sebastian Linnhoff-Popien, Claudia |
| author_facet | Kölle, Michael Feist, Alexander Stein, Jonas Wölckert, Sebastian Linnhoff-Popien, Claudia |
| contents | In recent years, neural networks (NNs) have driven significant advances in machine learning. However, as tasks grow more complex, NNs often require large numbers of trainable parameters, which increases computational and energy demands. Variational quantum circuits (VQCs) offer a promising alternative: they leverage quantum mechanics to capture intricate relationships and typically need fewer parameters. In this work, we evaluate NNs and VQCs on simple supervised and reinforcement learning tasks, examining models with different parameter sizes. We simulate VQCs and execute selected parts of the training process on real quantum hardware to approximate actual training times. Our results show that VQCs can match NNs in performance while using significantly fewer parameters, despite longer training durations. As quantum technology and algorithms advance, and VQC architectures improve, we posit that VQCs could become advantageous for certain machine learning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07273 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits Kölle, Michael Feist, Alexander Stein, Jonas Wölckert, Sebastian Linnhoff-Popien, Claudia Quantum Physics Artificial Intelligence Machine Learning In recent years, neural networks (NNs) have driven significant advances in machine learning. However, as tasks grow more complex, NNs often require large numbers of trainable parameters, which increases computational and energy demands. Variational quantum circuits (VQCs) offer a promising alternative: they leverage quantum mechanics to capture intricate relationships and typically need fewer parameters. In this work, we evaluate NNs and VQCs on simple supervised and reinforcement learning tasks, examining models with different parameter sizes. We simulate VQCs and execute selected parts of the training process on real quantum hardware to approximate actual training times. Our results show that VQCs can match NNs in performance while using significantly fewer parameters, despite longer training durations. As quantum technology and algorithms advance, and VQC architectures improve, we posit that VQCs could become advantageous for certain machine learning tasks. |
| title | Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits |
| topic | Quantum Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.07273 |