Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.27735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- We train an instantaneous quantum polynomial-time (IQP) Born machine on real high-energy-physics calorimeter shower images at $64$ qubits and compile the trained model into a single sampling-hard IQP circuit for quantum deployment. The pipeline has three components: a Mixture-of-IQP (\moiqp{}) architecture, whose Walsh-diagonal MMD$^{2}$ loss is classically trainable by Van den Nest Fourier Monte Carlo; the Pearson-Stabilized Correlation Kernel (\psck{}), a positive-definite MMD kernel that biases descent toward correlation-sensitive directions through a data-evaluated Jacobian of the empirical Pearson matrix; and an exact deferred-measurement compilation of \moiqp{} into a single IQP circuit on $\nfeat + \lceil \log_2 \Lcomp \rceil$ qubits (\ciqp{}). Across five seeds at $\Lcomp = 8$, $1500$ epochs, the model reaches $\maerho = 0.069 \pm 0.008$ against a $0.052$ encoding-fidelity floor on the training split and $0.071 \pm 0.008$ on a held-out test split, versus a Liu--Wang baseline at $\maerho = 0.100$. The compiled \ciqp{} reproduces the \moiqp{} marginal to $0.591 \pm 0.012$ times the Monte Carlo noise floor.