English

F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits

Quantum Physics 2021-10-11 v1 Machine Learning

Abstract

Generative modelling is an important unsupervised task in machine learning. In this work, we study a hybrid quantum-classical approach to this task, based on the use of a quantum circuit Born machine. In particular, we consider training a quantum circuit Born machine using ff-divergences. We first discuss the adversarial framework for generative modelling, which enables the estimation of any ff-divergence in the near term. Based on this capability, we introduce two heuristics which demonstrably improve the training of the Born machine. The first is based on ff-divergence switching during training. The second introduces locality to the divergence, a strategy which has proved important in similar applications in terms of mitigating barren plateaus. Finally, we discuss the long-term implications of quantum devices for computing ff-divergences, including algorithms which provide quadratic speedups to their estimation. In particular, we generalise existing algorithms for estimating the Kullback-Leibler divergence and the total variation distance to obtain a fault-tolerant quantum algorithm for estimating another ff-divergence, namely, the Pearson divergence.

Keywords

Cite

@article{arxiv.2110.04253,
  title  = {F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits},
  author = {Chiara Leadbeater and Louis Sharrock and Brian Coyle and Marcello Benedetti},
  journal= {arXiv preprint arXiv:2110.04253},
  year   = {2021}
}

Comments

20 pages, 9 figures, 4 tables

R2 v1 2026-06-24T06:44:42.460Z