Machine Learning Kernel Method from a Quantum Generative Model

TL;DR

This paper introduces a quantum sampling-based classifier leveraging randomized quantum circuits, demonstrating competitive performance with classical methods and highlighting quantum sampling as a promising avenue for quantum supremacy in machine learning.

Contribution

It proposes a novel quantum sampling approach for classification using randomized quantum circuits, combining quantum sampling with classical machine learning techniques.

Findings

Quantum sampling classifier performs at least as well as classical methods.

The method uses simple hyper-parameters and is easy to implement.

Quantum sampling is a promising task for achieving quantum supremacy.

Abstract

Recently the use of Noisy Intermediate Scale Quantum (NISQ) devices for machine learning tasks has been proposed. The propositions often perform poorly due to various restrictions. However, the quantum devices should perform well in sampling tasks. Thus, we recall theory of sampling-based approach to machine learning and propose a quantum sampling based classifier. Namely, we use randomized feature map approach. We propose a method of quantum sampling based on random quantum circuits with parametrized rotations distribution. We obtain simple to use method with intuitive hyper-parameters that performs at least equally well as top out-of-the-box classical methods. In short we obtain a competitive quantum classifier with crucial component being quantum sampling -- a promising task for quantum supremacy.