Quantum latent distributions in deep generative models

Omar Bacarreza, Thorin Farnsworth, Alexander Makarovskiy, Hugo Wallner, Tessa Hicks, Santiago Sempere-Llagostera, John J Price, Robert J. A. Francis-Jones, William R. Clements
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:4740-4760, 2026.

Abstract

Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple latent distributions are often used, the choice of distribution has a strong impact on model performance. Recent experiments have suggested that the probability distributions produced by quantum processors, which are typically highly correlated and classically intractable, can lead to improved performance on some datasets. However, when and why latent distributions produced by quantum processors can improve performance, and whether these improvements are connected to quantum properties of these distributions, are open questions that we investigate in this work. We show in theory that, under certain conditions, these "quantum latent distributions" enable generative models to produce data distributions that classical latent distributions cannot efficiently produce. We provide intuition as to the underlying mechanisms that could explain a performance advantage on real datasets. Based on this, we perform extensive benchmarking on a synthetic quantum dataset and the QM9 molecular dataset, using both simulated and real photonic quantum processors. We find that the statistics arising from quantum interference lead to improved generative performance compared to classical baselines, suggesting that quantum processors can play a role in expanding the capabilities of deep generative models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-bacarreza26a, title = {Quantum latent distributions in deep generative models}, author = {Bacarreza, Omar and Farnsworth, Thorin and Makarovskiy, Alexander and Wallner, Hugo and Hicks, Tessa and Sempere-Llagostera, Santiago and Price, John J and Francis-Jones, Robert J. A. and Clements, William R.}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {4740--4760}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/bacarreza26a/bacarreza26a.pdf}, url = {https://proceedings.mlr.press/v306/bacarreza26a.html}, abstract = {Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple latent distributions are often used, the choice of distribution has a strong impact on model performance. Recent experiments have suggested that the probability distributions produced by quantum processors, which are typically highly correlated and classically intractable, can lead to improved performance on some datasets. However, when and why latent distributions produced by quantum processors can improve performance, and whether these improvements are connected to quantum properties of these distributions, are open questions that we investigate in this work. We show in theory that, under certain conditions, these "quantum latent distributions" enable generative models to produce data distributions that classical latent distributions cannot efficiently produce. We provide intuition as to the underlying mechanisms that could explain a performance advantage on real datasets. Based on this, we perform extensive benchmarking on a synthetic quantum dataset and the QM9 molecular dataset, using both simulated and real photonic quantum processors. We find that the statistics arising from quantum interference lead to improved generative performance compared to classical baselines, suggesting that quantum processors can play a role in expanding the capabilities of deep generative models.} }
Endnote
%0 Conference Paper %T Quantum latent distributions in deep generative models %A Omar Bacarreza %A Thorin Farnsworth %A Alexander Makarovskiy %A Hugo Wallner %A Tessa Hicks %A Santiago Sempere-Llagostera %A John J Price %A Robert J. A. Francis-Jones %A William R. Clements %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-bacarreza26a %I PMLR %P 4740--4760 %U https://proceedings.mlr.press/v306/bacarreza26a.html %V 306 %X Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple latent distributions are often used, the choice of distribution has a strong impact on model performance. Recent experiments have suggested that the probability distributions produced by quantum processors, which are typically highly correlated and classically intractable, can lead to improved performance on some datasets. However, when and why latent distributions produced by quantum processors can improve performance, and whether these improvements are connected to quantum properties of these distributions, are open questions that we investigate in this work. We show in theory that, under certain conditions, these "quantum latent distributions" enable generative models to produce data distributions that classical latent distributions cannot efficiently produce. We provide intuition as to the underlying mechanisms that could explain a performance advantage on real datasets. Based on this, we perform extensive benchmarking on a synthetic quantum dataset and the QM9 molecular dataset, using both simulated and real photonic quantum processors. We find that the statistics arising from quantum interference lead to improved generative performance compared to classical baselines, suggesting that quantum processors can play a role in expanding the capabilities of deep generative models.
APA
Bacarreza, O., Farnsworth, T., Makarovskiy, A., Wallner, H., Hicks, T., Sempere-Llagostera, S., Price, J.J., Francis-Jones, R.J.A. & Clements, W.R.. (2026). Quantum latent distributions in deep generative models. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:4740-4760 Available from https://proceedings.mlr.press/v306/bacarreza26a.html.

Related Material