We introduce a random circuit family and show they are robust against current classical simulation techniques, specifically tensor network contraction and Pauli propagation. We also show that local variables do not concentrate, ensuring enough variance to be able to produce a diverse set of data points. We therefore argue that using these circuits as a "random seed" for a larger classical generative model is a way to make large-scale quantum-classical hybrid models amenable towards NISQ devices.
Cite
@article{arxiv.2602.10049,
title = {Random Quantum Circuits as Seeds for Continuous Generative Models},
author = {Olli Hirviniemi and Afrad Basheer and Thomas Cope},
journal= {arXiv preprint arXiv:2602.10049},
year = {2026}
}
Comments
Article is substantially expanded. Addition of numerical studies of classical simulation methods, stronger proofs, clearer connections to prior work and the core concept is elaborated upon