Get the latest tech news

Quantum machine learning via vector embeddings


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.

View a PDF of the paper titled Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning, by Sebasti\'an Andr\'es Cajas Ord\'o\~nez and 4 other authors 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.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of quantum

quantum

Photo of vector embeddings

vector embeddings

Related news:

News photo

Microsoft CEO sends a surprising message on quantum computing

News photo

Scientists have discovered a way to make quantum entanglement reversible, something long thought to be impossible, via a quantum entanglement battery device

News photo

Fujitsu Starts Development of 10,000-plus Qubit Superconducting Quantum Computer, Completion Expected in 2030