Quantum circuit-like learning: A fast and scalable classical machine-learning algorithm with similar performance to quantum circuit learning

TL;DR

This paper introduces a classical machine learning algorithm inspired by quantum circuit learning, achieving similar performance to quantum methods while being faster and more scalable on classical hardware.

Contribution

A novel classical algorithm mimics quantum circuit learning using count sketch, offering comparable performance with improved efficiency.

Findings

Classical algorithm matches quantum circuit learning performance on several tasks.

The proposed method is faster and more scalable than quantum implementations.

Provides insights into the efficiency comparison between quantum and classical ML algorithms.

Abstract

The application of near-term quantum devices to machine learning (ML) has attracted much attention. In one such attempt, Mitarai et al. (2018) proposed a framework to use a quantum circuit for supervised ML tasks, which is called quantum circuit learning (QCL). Due to the use of a quantum circuit, QCL can employ an exponentially high-dimensional Hilbert space as its feature space. However, its efficiency compared to classical algorithms remains unexplored. In this study, using a statistical technique called count sketch, we propose a classical ML algorithm that uses the same Hilbert space. In numerical simulations, our proposed algorithm demonstrates similar performance to QCL for several ML tasks. This provides a new perspective with which to consider the computational and memory efficiency of quantum ML algorithms.