quant-phFeb 11, 2026

Characterizing the Trainability of Instantaneous Quantum Polynomial Circuit Born Machines

Authors: Kevin Shen, Susanne Pielawa, Vedran Dunjko, Hao Wang

Organizations: ⟨aQaL⟩Applied Quantum Algorithms, Leiden University, The Netherlands · LIACS, Leiden University, Niels Bohrweg 1, 2333 CA, Leiden, The Netherlands · BMW Group, 80788 München, Germany

Abstract

Instantaneous Quantum Polynomial Circuit Born Machines (IQP-QCBMs) have been proposed as quantum generative models that combine a classically tractable training objective - based on the maximum mean discrepancy (MMD) - with a potential quantum advantage motivated by sampling-complexity arguments. While recent works have explored this model across various application domains, fundamental questions remain: does the model suffer from exponentially vanishing loss gradients, known as the barren plateau problem - a pervasive obstacle in quantum machine learning - and how do regimes of trainability relate to regimes of possible quantum advantage? Here, we address both questions analytically. To study trainability, we derive closed-form expressions for the variances of the partial derivatives of the MMD loss function and establish general upper and lower bounds. We explicitly characterize how trainability depends on the generator set and the spectrum of the chosen kernel, identifying regimes in which low Hamming-weight kernels avoid exponential gradient suppression under structured topologies. Regarding potential quantum advantage, we reformulate the anti-concentration property in terms of the same generator-set quantities that govern trainability, enabling a unified analysis. We show that sparse IQP architectures can produce classically intractable output distributions while simultaneously remaining trainable, at least at lower-weight frequencies. Our analytical results corroborate the numerical observations of prior work and provide principled guidelines for designing scalable IQP-QCBM architectures.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization

    Jun 8, 2026Gennaro De Luca, Vinayak Sharma, Aviral ShrivastavaQuantum Generative ModelingQuantum Machine Learning

  2. IQP Born Machines under Data-dependent and Agnostic Initialization Strategies

    Mar 15, 2026Sacha Lerch, Joseph Bowles, Ricard Puig +3Quantum Circuit Born MachinesQuantum Machine Learning

  3. Classical training of conditional instantaneous quantum polynomial-time Born machines

    Nov 3, 2026Oriol Balló-Gimbernat, Emiliano Tolotti, Laia Domingo +2Quantum Generative ModelingQuantum Circuit Born Machines