English

Sample-based training of quantum generative models

Quantum Physics 2025-11-18 v1

Abstract

Quantum computers can efficiently sample from probability distributions that are believed to be classically intractable, providing a foundation for quantum generative modeling. However, practical training of such models remains challenging, as gradient evaluation via the parameter-shift rule scales linearly with the number of parameters and requires repeated expectation-value estimation under finite-shot noise. We introduce a training framework that extends the principle of contrastive divergence to quantum models. By deriving the circuit structure and providing a general recipe for constructing it, we obtain quantum circuits that generate the samples required for parameter updates, yielding constant scaling with respect to the cost of a forward pass, analogous to backpropagation in classical neural networks. Numerical results demonstrate that it attains comparable accuracy to likelihood-based optimization while requiring substantially fewer samples. The framework thereby establishes a scalable route to training expressive quantum generative models directly on quantum hardware.

Keywords

Cite

@article{arxiv.2511.11802,
  title  = {Sample-based training of quantum generative models},
  author = {Maria Demidik and Cenk Tüysüz and Michele Grossi and Karl Jansen},
  journal= {arXiv preprint arXiv:2511.11802},
  year   = {2025}
}

Comments

10 pages, 3 figures; supplementary material 6 pages, 3 figures

R2 v1 2026-07-01T07:38:18.835Z