Abstract
Abstract
We quantify the role of scrambling in quantum machine learning. We characterize a quantum neural network’s (QNNs) error in terms of the network’s scrambling properties via the out-of-time-ordered correlator (OTOC). A network can be trained by minimizing a loss function. We show that the loss function can be bounded by the OTOC. We prove that the gradient of the loss function can be bounded by the gradient of the OTOC. This demonstrates that the OTOC landscape regulates the trainability of a QNN. We show numerically that this landscape is flat for maximally scrambling QNNs, which can pose a challenge to training. Our results pave the way for the exploration of quantum chaos in quantum neural networks.
Publisher
Springer Science and Business Media LLC
Subject
Nuclear and High Energy Physics
Reference66 articles.
1. M. Schuld, I. Sinayskiy and F. Petruccione, Simulating a perceptron on a quantum computer, Phys. Lett. A 379 (2015) 660.
2. K. H. Wan, O. Dahlsten, H. Kristjánsson, R. Gardner and M. S. Kim, Quantum generalisation of feedforward neural networks, npj Quantum Inf. 3 (2017) 36.
3. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe and S. Lloyd, Quantum machine learning, Nature 549 (2017) 195.
4. E. Farhi and H. Neven, Classification with quantum neural networks on near term processors, arXiv:1802.06002.
5. I. Cong, S. Choi and M. D. Lukin, Quantum convolutional neural networks, Nature Phys. 15 (2019) 1273.
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献