Quantum-Train: Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911911494287360 |
|---|---|
| author | Liu, Chen-Yu Kuo, En-Jui Lin, Chu-Hsuan Abraham Young, Jason Gemsun Chang, Yeong-Jar Hsieh, Min-Hsiu Goan, Hsi-Sheng |
| author_facet | Liu, Chen-Yu Kuo, En-Jui Lin, Chu-Hsuan Abraham Young, Jason Gemsun Chang, Yeong-Jar Hsieh, Min-Hsiu Goan, Hsi-Sheng |
| contents | We introduces the Quantum-Train(QT) framework, a novel approach that integrates quantum computing with classical machine learning algorithms to address significant challenges in data encoding, model compression, and inference hardware requirements. Even with a slight decrease in accuracy, QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model, which significantly reduces the parameter count from $M$ to $O(\text{polylog} (M))$ during training. Our experiments demonstrate QT's effectiveness in classification tasks, offering insights into its potential to revolutionize machine learning by leveraging quantum computational advantages. This approach not only improves model efficiency but also reduces generalization errors, showcasing QT's potential across various machine learning applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11304 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantum-Train: Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective Liu, Chen-Yu Kuo, En-Jui Lin, Chu-Hsuan Abraham Young, Jason Gemsun Chang, Yeong-Jar Hsieh, Min-Hsiu Goan, Hsi-Sheng Quantum Physics We introduces the Quantum-Train(QT) framework, a novel approach that integrates quantum computing with classical machine learning algorithms to address significant challenges in data encoding, model compression, and inference hardware requirements. Even with a slight decrease in accuracy, QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model, which significantly reduces the parameter count from $M$ to $O(\text{polylog} (M))$ during training. Our experiments demonstrate QT's effectiveness in classification tasks, offering insights into its potential to revolutionize machine learning by leveraging quantum computational advantages. This approach not only improves model efficiency but also reduces generalization errors, showcasing QT's potential across various machine learning applications. |
| title | Quantum-Train: Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2405.11304 |