An IQP Born Machine for Calorimeter Image Generation at 64 Qubits with Compiled-IQP Deployment

Abstract: 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$<sup>{2}$ 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.