English

Quantifying scrambling in quantum neural networks

Quantum Physics 2022-03-23 v2 High Energy Physics - Theory

Abstract

We characterize a quantum neural network's error in terms of the network's scrambling properties via the out-of-time-ordered correlator. A network can be trained by optimizing either a loss function or a cost function. We show that, with some probability, both functions can be bounded by out-of-time-ordered correlators. The gradients of these functions can be bounded by the gradient of the out-of-time-ordered correlator, demonstrating that the network's scrambling ability governs its trainability. Our results pave the way for the exploration of quantum chaos in quantum neural networks.

Keywords

Cite

@article{arxiv.2112.01440,
  title  = {Quantifying scrambling in quantum neural networks},
  author = {Roy J. Garcia and Kaifeng Bu and Arthur Jaffe},
  journal= {arXiv preprint arXiv:2112.01440},
  year   = {2022}
}
R2 v1 2026-06-24T08:02:03.176Z