Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning

TL;DR

This paper introduces an embedding-aware quantum-classical pipeline that leverages Vision Transformer embeddings to achieve quantum advantage in scalable quantum machine learning, demonstrating significant accuracy improvements on standard datasets.

Contribution

It presents a novel integration of pretrained Vision Transformer embeddings with quantum SVMs, showing that embedding choice critically influences quantum advantage and scalability.

Findings

ViT embeddings enable quantum advantage with up to 8.02% accuracy improvement.

Quantum advantage depends critically on embedding choice, especially transformer-based embeddings.

The approach offers a practical pathway for scalable quantum machine learning leveraging neural architectures.

Abstract

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.