Classical training of conditional instantaneous quantum polynomial-time Born machines
Abstract
Instantaneous quantum polynomial-time (IQP) Born machines are attractive quantum generative models, as certain IQP circuit families are conjectured to be hard to sample, yet they can be trained classically. Previously proposed conditional IQP Born machines make the parameters of the diagonal layer condition dependent. We introduce conditional IQP Born machines, in which the condition is encoded in the input state and a single IQP unitary is shared across conditions. Efficient sampling and amplitude-ratio evaluation for the reference state entering the diagonal layer suffice to obtain unbiased classical estimates of a conditional maximum mean discrepancy objective and its gradients. We show that input conditioning can represent conditional families that no diagonally conditioned IQP model with the same number of qubits can reproduce. For the sixteen-qubit Curie-Weiss spin model, a single conditional model captures the magnetization transition at held-out temperatures. Its mean total variation distance is six times lower than that of diagonal conditioning under the same protocol and comparable to that of classical generative models with up to seven times as many parameters. We also train conditional models classically with up to 2048 qubits, which reproduce the mean squared magnetization of the target away from the crossover. These results extend classically trained IQP Born machines to conditional generation.
Related
- Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
- Performance analysis of classical adiabatic annealing on Ising machines
- The Classical Boundary of Quantum Computation: History-Resolved Causal Stochastic Machines and the Cost of Classicalization
- Noise-regularized training of quantum circuit Born machines under a finite shot budget
- Universal Scaling of Conditional Mutual Information in Classical Stochastic Dynamics
BibTeX
@misc{ballogimbernat2026classical,
title = {{Classical training of conditional instantaneous quantum polynomial-time Born machines}},
author = {Oriol Balló-Gimbernat and Emiliano Tolotti and Laia Domingo and Fernando Vilariño and Adan Garriga},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.05483},
eprint = {2611.05483},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.05483},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Classical training of conditional instantaneous quantum polynomial-time Born machines
AU - Oriol Balló-Gimbernat
AU - Emiliano Tolotti
AU - Laia Domingo
AU - Fernando Vilariño
AU - Adan Garriga
PY - 2026
DA - 2026/11/03
PB - arXiv
DO - 10.48550/arxiv.2611.05483
UR - https://arxiv.org/abs/2611.05483
AB - Instantaneous quantum polynomial-time (IQP) Born machines are attractive quantum generative models, as certain IQP circuit families are conjectured to be hard to sample, yet they can be trained classically. Previously proposed conditional IQP Born machines make the parameters of the diagonal layer condition dependent. We introduce conditional IQP Born machines, in which the condition is encoded in the input state and a single IQP unitary is shared across conditions. Efficient sampling and amplitude-ratio evaluation for the reference state entering the diagonal layer suffice to obtain unbiased classical estimates of a conditional maximum mean discrepancy objective and its gradients. We show that input conditioning can represent conditional families that no diagonally conditioned IQP model with the same number of qubits can reproduce. For the sixteen-qubit Curie-Weiss spin model, a single conditional model captures the magnetization transition at held-out temperatures. Its mean total variation distance is six times lower than that of diagonal conditioning under the same protocol and comparable to that of classical generative models with up to seven times as many parameters. We also train conditional models classically with up to 2048 qubits, which reproduce the mean squared magnetization of the target away from the crossover. These results extend classically trained IQP Born machines to conditional generation.
ER -