Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning
This provides a practical pathway for scalable quantum machine learning that leverages modern neural architectures, addressing a bottleneck for researchers in quantum ML.
The paper tackles scalability challenges in Quantum Support Vector Machines by proposing an embedding-aware quantum-classical pipeline that combines class-balanced k-means distillation with pretrained Vision Transformer embeddings, achieving up to 8.02% accuracy improvement over classical SVMs on Fashion-MNIST and 4.42% on MNIST.
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.