Randomness-Enhanced Expressivity of Quantum Neural Networks

Wu，Yadong1,2,3; Yao，Juan4,5,6; Zhang，Pengfei1,3; Li，Xiaopeng1,2,3,7,8

2024-01-05

10.1103/PhysRevLett.132.010602

Physical Review Letters   影响因子和分区

0031-9007

1079-7114

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 devices. Conventional QNNs are described by parametrized quantum circuits, which perform unitary operations and measurements on quantum states. In this Letter, 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 a 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.

SCI ; EI

英语

其他

PHYSICS

2-s2.0-85182810163

Scopus

1.Department of Physics,Fudan University,Shanghai,200438,China
2.State Key Laboratory of Surface Physics,Key Laboratory of Micro and Nano Photonic Structures (MOE),Institute for Nanoelectronic Devices and Quantum Computing,Fudan University,Shanghai,200438,China
3.Shanghai Qi Zhi Institute,Shanghai,AI Tower, Xuhui District,200232,China
4.Shenzhen Institute for Quantum Science and Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,518055,China
5.International Quantum Academy,Shenzhen,Guangdong,518048,China
6.Guangdong Provincial Key Laboratory of Quantum Science and Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,518055,China
7.Shanghai Artificial Intelligence Laboratory,Shanghai,200232,China
8.Shanghai Research Center for Quantum Sciences,Shanghai,201315,China

Wu，Yadong,Yao，Juan,Zhang，Pengfei,et al. Randomness-Enhanced Expressivity of Quantum Neural Networks[J]. Physical Review Letters,2024,132(1).

Wu，Yadong,Yao，Juan,Zhang，Pengfei,&Li，Xiaopeng.(2024).Randomness-Enhanced Expressivity of Quantum Neural Networks.Physical Review Letters,132(1).

Wu，Yadong,et al."Randomness-Enhanced Expressivity of Quantum Neural Networks".Physical Review Letters 132.1(2024).