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

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.

16 pages, 10 figures

References in corpus (12)

• Quantum algorithm for solving linear systems of equations
• Quantum Convolutional Neural Networks
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Parameterized quantum circuits as machine learning models
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Information-theoretic bounds on quantum advantage in machine learning
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Quantum reservoir processing
• Quantum generative adversarial learning in a superconducting quantum circuit
• Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions
• Learning and Inference on Generative Adversarial Quantum Circuits
• Improved Bounds on Quantum Learning Algorithms