Conditioning in generative quantum denoising diffusion models

Year: 2026

Authors: Quinn D., Buffoni L., Gherardini S., De Chiara G.

Autors Affiliation: Queens Univ Belfast, Ctr Quantum Mat & Technol, Sch Math & Phys, Belfast, North Ireland; Univ Florence, Dept Phys & Astron, Sesto Fiorentino, Italy; Ist Nazl Ott INO, Consiglio Nazl Ric CNR, Fiorentino, Italy; Univ Firenze, European Lab Nonlinear Spect, Sesto Fiorentino, Italy; Univ Autonoma Barcelona, Dept Fis, Fis Teorica Informacio & Fenomens Quant, Bellaterra, Spain.

Abstract: Quantum denoising diffusion models have recently emerged as a powerful framework for generative quantum machine learning. In this work, we extend these models by introducing a conditioning mechanism that enables the generation of quantum states drawn from multiple target distributions. By sharing parameters across distinct classes of quantum states, our approach avoids the need to train separate models for each distribution. We validate our method through numerical simulations that span single-qubit generation tasks, entangled state preparation, and many-body ground state generation. Across these tasks, conditioning significantly reduced the error of targeted state generation by more than an order of magnitude. Finally, we perform an ablation study to quantify the effect of key hyperparameters on the model performance.

Journal/Review: QUANTUM SCIENCE AND TECHNOLOGY

Volume: 11 (3)      Pages from: 35047-1  to: 35047-21

More Information: D. Q. acknowledges support from the UK EPSRC through Grant No. EP/W52444X/1 and is grateful for use of the computing resources from the Northern Ireland High Performance Computing (NI-HPC) service funded by UK EPSRC Grant No. EP/T022175. G.D.C. acknowledges financial support from the Spanish Agencia Estatal de Investigacion project PID2024-162153NB-I00 and UKRI-EPSRC project UKRI3314. The authors thankfully acknowledge the computer resources at MareNostrum and the technical support provided by Barcelona Supercomputing Centre (FI-2025-2-0017).
KeyWords: quantum denoising diffusion models; generative models; quantum machine learning; quantum computing
DOI: 10.1088/2058-9565/ae8881