Noise-regularized training of quantum circuit Born machines under a finite shot budget
Abstract
Quantum circuit Born machines (QCBMs) can learn distributions that are hard to sample from classically, but their value depends on generalizing from finite training data. Here, we study how hardware noise affects this generalization. We show that, for any noise process, the generalization gap of a QCBM trained with the maximum mean discrepancy is bounded by the complexity of the distributions the noisy model can reach. Scrambled local Pauli noise contracts this complexity but biases the model towards the uniform distribution, so residual noise acts as a regularizer whose optimal strength can be intermediate. We propose GENIE, a framework that realizes a chosen noise level with capped error mitigation and selects it during training from held-out data within a fixed execution budget, with provably bounded regret. In simulations on synthetic and census data, GENIE stays close to the best of four noise-control strategies, whereas every fixed noise level falls short in many settings.
Related
- Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
- Nonstabilizerness of the entangling layer in quantum circuit Born machines
- Classical training of conditional instantaneous quantum polynomial-time Born machines
- Finite attainment and efficient computation of regularized quantum channel relative entropy
- Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers
BibTeX
@misc{ngo2026noiseregularized,
title = {{Noise-regularized training of quantum circuit Born machines under a finite shot budget}},
author = {Hoang M. Ngo and Quan Nguyen and Jung Taek Seo and Wanli Xing and My T. Thai},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.06630},
eprint = {2611.06630},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.06630},
}
RIS
TY - UNPB
TI - Noise-regularized training of quantum circuit Born machines under a finite shot budget
AU - Hoang M. Ngo
AU - Quan Nguyen
AU - Jung Taek Seo
AU - Wanli Xing
AU - My T. Thai
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.06630
UR - https://arxiv.org/abs/2611.06630
AB - Quantum circuit Born machines (QCBMs) can learn distributions that are hard to sample from classically, but their value depends on generalizing from finite training data. Here, we study how hardware noise affects this generalization. We show that, for any noise process, the generalization gap of a QCBM trained with the maximum mean discrepancy is bounded by the complexity of the distributions the noisy model can reach. Scrambled local Pauli noise contracts this complexity but biases the model towards the uniform distribution, so residual noise acts as a regularizer whose optimal strength can be intermediate. We propose GENIE, a framework that realizes a chosen noise level with capped error mitigation and selects it during training from held-out data within a fixed execution budget, with provably bounded regret. In simulations on synthetic and census data, GENIE stays close to the best of four noise-control strategies, whereas every fixed noise level falls short in many settings.
ER -