Randomness-enhanced expressivity of quantum neural networks

Abstract

As a hybrid of artificial intelligence and quantum computing, quantum neural networks (QNNs) have gained significant attention as a promising application on near-term, noisy intermediate-scale quantum (NISQ) devices. Conventional QNNs are described by parametrized quantum circuits, which perform unitary operations and measurements on quantum states. In this work, we propose a novel approach to enhance the expressivity of QNNs by incorporating randomness into quantum circuits. Specifically, we introduce a random layer, which contains single-qubit gates sampled from an trainable ensemble pooling. The prediction of QNN is then represented by an ensemble average over a classical function of measurement outcomes. We prove that our approach can accurately approximate arbitrary target operators using Uhlmann's theorem for majorization, which enables observable learning. Our proposal is demonstrated with extensive numerical experiments, including observable learning, Rényi entropy measurement, and image recognition. We find the expressivity of QNNs is enhanced by introducing randomness for multiple learning tasks, which could have broad application in quantum machine learning.

6 pages, 4 figures

References in corpus (22)

• The effect of data encoding on the expressive power of variational quantum machine learning models
• Generalization in quantum machine learning from few training data
• Quantum convolutional neural network for classical data classification
• The randomized measurement toolbox
• Observation of measurement-induced quantum phases in a trapped-ion quantum computer
• Provably efficient machine learning for quantum many-body problems
• Experimental Realization of a Measurement-Induced Entanglement Phase Transition on a Superconducting Quantum Processor
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Fermionic partial tomography via classical shadows
• Robust shadow estimation
• Classical Shadows With Noise
• Experimental Estimation of Quantum State Properties from Classical Shadows
• Classical Shadow Tomography with Locally Scrambled Quantum Dynamics
• Matchgate Shadows for Fermionic Quantum Simulation
• Scalable and Flexible Classical Shadow Tomography with Tensor Networks
• Shadow process tomography of quantum channels
• Expressivity of Quantum Neural Networks
• Operator relaxation and the optimal depth of classical shadows
• Scrambling Ability of Quantum Neural Networks Architectures
• Closed-form analytic expressions for shadow estimation with brickwork circuits
• A duplication-free quantum neural network for universal approximation
• On Classical and Hybrid Shadows of Quantum States

Cited by in corpus (8)

• Nonstabilizerness via matrix product states in the Pauli basis
• Digital-analog quantum convolutional neural networks for image classification
• Variational Tensor Neural Networks for Deep Learning
• Variational measurement-based quantum computation for generative modeling
• Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
• Machine-Learning Insights into the Entanglement-trainability Correlation of Parameterized Quantum Circuits
• Channel Attention for Quantum Convolutional Neural Networks
• Measuring Incompatible Observables with Quantum Neural Networks