English

Barren plateaus preclude learning scramblers

Quantum Physics 2021-10-20 v3 General Relativity and Quantum Cosmology High Energy Physics - Theory

Abstract

Scrambling processes, which rapidly spread entanglement through many-body quantum systems, are difficult to investigate using standard techniques, but are relevant to quantum chaos and thermalization. In this Letter, we ask if quantum machine learning (QML) could be used to investigate such processes. We prove a no-go theorem for learning an unknown scrambling process with QML, showing that any variational ansatz is highly probable to have a barren plateau landscape, i.e., cost gradients that vanish exponentially in the system size. This implies that the required resources scale exponentially even when strategies to avoid such scaling (e.g., from ansatz-based barren plateaus or No-Free-Lunch theorems) are employed. Furthermore, we numerically and analytically extend our results to approximate scramblers. Hence, our work places generic limits on the learnability of unitaries when lacking prior information.

Keywords

Cite

@article{arxiv.2009.14808,
  title  = {Barren plateaus preclude learning scramblers},
  author = {Zoë Holmes and Andrew Arrasmith and Bin Yan and Patrick J. Coles and Andreas Albrecht and Andrew T. Sornborger},
  journal= {arXiv preprint arXiv:2009.14808},
  year   = {2021}
}

Comments

5 pages, 3 figures in the main text. 6 pages, 1 figure in the supplementary information. Comments welcome

R2 v1 2026-06-23T18:54:58.150Z