A Quantum Information Theoretic Approach to Tractable Probabilistic Models
Abstract
By recursively nesting sums and products, probabilistic circuits have emerged in recent years as an attractive class of generative models as they enjoy, for instance, polytime marginalization of random variables. In this work we study these machine learning models using the framework of quantum information theory, leading to the introduction of positive unital circuits (PUnCs), which generalize circuit evaluations over positive real-valued probabilities to circuit evaluations over positive semi-definite matrices. As a consequence, PUnCs strictly generalize probabilistic circuits as well as recently introduced circuit classes such as PSD circuits.
Cite
Text
Zuidberg Dos Martires. "A Quantum Information Theoretic Approach to Tractable Probabilistic Models." Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, 2025.Markdown
[Zuidberg Dos Martires. "A Quantum Information Theoretic Approach to Tractable Probabilistic Models." Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, 2025.](https://mlanthology.org/uai/2025/zuidbergdosmartires2025uai-quantum/)BibTeX
@inproceedings{zuidbergdosmartires2025uai-quantum,
title = {{A Quantum Information Theoretic Approach to Tractable Probabilistic Models}},
author = {Zuidberg Dos Martires, Pedro},
booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence},
year = {2025},
pages = {3013-3030},
volume = {286},
url = {https://mlanthology.org/uai/2025/zuidbergdosmartires2025uai-quantum/}
}