Markovian Quantum Neuroevolution for Machine Learning

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.

arXiv comment7 pages (main text) + 5.5 pages (supplementary materials), 14 figures

References in corpus (57)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Machine learning and the physical sciences
• Barren plateaus in quantum neural network training landscapes
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Machine learning phases of matter
• Quantum principal component analysis
• Circuit-centric quantum classifiers
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Quantum Approximate Optimization Algorithm: Performance, Mechanism, and Implementation on Near-Term Devices
• Quantum optimization using variational algorithms on near-term quantum devices
• Discovering Phase Transitions with Unsupervised Learning
• Self-Verifying Variational Quantum Simulation of the Lattice Schwinger Model
• Quantum generative adversarial learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum-enhanced machine learning
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Machine learning quantum phases of matter beyond the fermion sign problem
• Quantum Boltzmann Machine
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Reconstructing quantum states with generative models
• Hierarchical quantum classifiers
• Differentiable Learning of Quantum Circuit Born Machine
• Quantum generalisation of feedforward neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Quantum Loop Topography for Machine Learning
• Learning the quantum algorithm for state overlap
• Machine Learning Phases of Strongly Correlated Fermions
• Implementing a distance-based classifier with a quantum interference circuit
• Accelerated Variational Quantum Eigensolver
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Quantum generative adversarial learning in a superconducting quantum circuit
• Machine learning meets quantum physics
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Variational Quantum Eigensolver with Fewer Qubits
• Suppression of photon shot noise dephasing in a tunable coupling superconducting qubit
• Quantum Adversarial Machine Learning
• Statistical mechanics of the Cluster-Ising model
• Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Quantum Optimization with a Novel Gibbs Objective Function and Ansatz Architecture Search
• Topological Quantum Compiling with Reinforcement Learning
• Vulnerability of quantum classification to adversarial perturbations
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Approximate Quantum Adders with Genetic Algorithms: An IBM Quantum Experience
• A Domain-agnostic, Noise-resistant, Hardware-efficient Evolutionary Variational Quantum Eigensolver

Cited by in corpus (11)

• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Observation of a symmetry-protected topological time crystal with superconducting qubits
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Recent advances for quantum classifiers
• Neural Predictor based Quantum Architecture Search
• Variational Quantum-Neural Hybrid Eigensolver
• Quantum Architecture Search with Meta-learning
• Quantum Capsule Networks
• Hierarchical quantum circuit representations for neural architecture search
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Exploring the optimality of approximate state preparation quantum circuits with a genetic algorithm