Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909894653771776 |
|---|---|
| author | Ordóñez, Sebastián Andrés Cajas Torres, Luis Fernando Torres Bifulco, Mario Durán, Carlos Andrés Bosch, Cristian Carbajo, Ricardo Simón |
| author_facet | Ordóñez, Sebastián Andrés Cajas Torres, Luis Fernando Torres Bifulco, Mario Durán, Carlos Andrés Bosch, Cristian Carbajo, Ricardo Simón |
| contents | Quantum Support Vector Machines face scalability challenges due to high-dimensional quantum states and hardware limitations. We propose an embedding-aware quantum-classical pipeline combining class-balanced k-means distillation with pretrained Vision Transformer embeddings. Our key finding: ViT embeddings uniquely enable quantum advantage, achieving up to 8.02% accuracy improvements over classical SVMs on Fashion-MNIST and 4.42% on MNIST, while CNN features show performance degradation. Using 16-qubit tensor network simulation via cuTensorNet, we provide the first systematic evidence that quantum kernel advantage depends critically on embedding choice, revealing fundamental synergy between transformer attention and quantum feature spaces. This provides a practical pathway for scalable quantum machine learning that leverages modern neural architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00024 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning Ordóñez, Sebastián Andrés Cajas Torres, Luis Fernando Torres Bifulco, Mario Durán, Carlos Andrés Bosch, Cristian Carbajo, Ricardo Simón Quantum Physics Artificial Intelligence Machine Learning Quantum Support Vector Machines face scalability challenges due to high-dimensional quantum states and hardware limitations. We propose an embedding-aware quantum-classical pipeline combining class-balanced k-means distillation with pretrained Vision Transformer embeddings. Our key finding: ViT embeddings uniquely enable quantum advantage, achieving up to 8.02% accuracy improvements over classical SVMs on Fashion-MNIST and 4.42% on MNIST, while CNN features show performance degradation. Using 16-qubit tensor network simulation via cuTensorNet, we provide the first systematic evidence that quantum kernel advantage depends critically on embedding choice, revealing fundamental synergy between transformer attention and quantum feature spaces. This provides a practical pathway for scalable quantum machine learning that leverages modern neural architectures. |
| title | Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning |
| topic | Quantum Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.00024 |