A

Parameterized quantum circuits as universal generative models for continuous multivariate distributions

npj Quantum Information, vol. 11, pp. 121

Abstract

Parameterized quantum circuits are a key component of quantum machine learning models for regression, classification, and generative tasks. Quantum Circuit Born machines produce discrete distributions over bitstrings whose length is exactly the number of qubits. To allow for distributions on continuous variables, new models have been introduced where classical randomness is uploaded into quantum circuits and expectation values are returned with a dimensionality decoupled from qubit number. While these models have been explored experimentally, their expressivity remains underexplored. In this work, we formalize this family and establish its theoretical foundation. We prove the universality of several variational circuit architectures for generating continuous multivariate distributions and derive tight resource bounds to reach universality using tools related to the Holevo bound. Our results reveal a trade-off between the number of qubits and measurements. We further explore relaxed notions of universality and present a practical use case, outlining potential domains for quantum advantage.

Authors 5

  1. Leiden University · European Organization for Nuclear Research

    Affiliation as printed

    Applied Quantum Algorithms, Universiteit Leiden, Leiden, the Netherlands

    Instituut-Lorentz, Universiteit Leiden, Leiden, the Netherlands

    Quantum Technology Initiative, CERN, Geneva, Switzerland

  2. European Organization for Nuclear Research

    Affiliation as printed

    Quantum Technology Initiative, CERN, Geneva, Switzerland

  3. European Organization for Nuclear Research

    Affiliation as printed

    Quantum Technology Initiative, CERN, Geneva, Switzerland

  4. Leiden University

    Affiliation as printed

    Applied Quantum Algorithms, Universiteit Leiden, Leiden, the Netherlands

    Instituut-Lorentz, Universiteit Leiden, Leiden, the Netherlands

  5. Leiden University

    Affiliation as printed

    Applied Quantum Algorithms, Universiteit Leiden, Leiden, the Netherlands

    Instituut-Lorentz, Universiteit Leiden, Leiden, the Netherlands

Cited by 11 stored of 11

11 results

No patents citing this paper on Lens.org (checked 2026-10-11).

References 31