Markovian Quantum Neuroevolution for Machine Learning

TL;DR

This paper introduces a quantum neuroevolution algorithm that autonomously discovers near-optimal quantum neural networks for various machine learning tasks, leveraging a Markovian process to optimize quantum circuit structures.

Contribution

It establishes a novel mapping between quantum circuits and directed graphs, enabling efficient quantum architecture search through a Markovian search process.

Findings

Successfully classified real-life images using quantum neural networks.

Demonstrated the algorithm's effectiveness on symmetry-protected topological states.

Showcased potential for quantum architecture search on noisy intermediate-scale quantum devices.

Abstract

Neuroevolution, a field that draws inspiration from the evolution of brains in nature, harnesses evolutionary algorithms to construct artificial neural networks. It bears a number of intriguing capabilities that are typically inaccessible to gradient-based approaches, including optimizing neural-network architectures, hyperparameters, and even learning the training rules. In this paper, we introduce a quantum neuroevolution algorithm that autonomously finds near-optimal quantum neural networks for different machine-learning tasks. In particular, we establish a one-to-one mapping between quantum circuits and directed graphs, and reduce the problem of finding the appropriate gate sequences to a task of searching suitable paths in the corresponding graph as a Markovian process. We benchmark the effectiveness of the introduced algorithm through concrete examples including classifications of real-life images and symmetry-protected topological states. Our results showcase the vast potential of neuroevolution algorithms in quantum architecture search, which would boost the exploration towards quantum-learning advantage with noisy intermediate-scale quantum devices.