Random probabilistic circuits

Nicola Di Mauro, Gennaro Gala, Marco Iannotta, Teresa M.A. Basile
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, PMLR 161:1682-1691, 2021.

Abstract

Density estimation could be viewed as a core component in machine learning, since a good estimator could be used to solve many tasks such as classification, regression, and imputing missing values. The main challenge of density estimation is balancing the model expressiveness and its learning and inference complexity. Probabilistic circuits (PCs) model a probability distribution as a computational graph. By imposing specific structural properties on such models many inference tasks become tractable. However, learning PCs usually relies on greedy and time consuming procedures. In this paper we propose a new unified approach to efficiently learn PCs having several structural properties. We introduce extremely randomized PCs (XPCs), PCs with a random structure. We show their advantage on standard density estimation benchmarks when compared to other density estimators.

Cite this Paper

BibTeX
@InProceedings{pmlr-v161-di-mauro21a, title = {Random probabilistic circuits}, author = {Di Mauro, Nicola and Gala, Gennaro and Iannotta, Marco and Basile, Teresa M.A.}, booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence}, pages = {1682--1691}, year = {2021}, editor = {de Campos, Cassio and Maathuis, Marloes H.}, volume = {161}, series = {Proceedings of Machine Learning Research}, month = {27--30 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v161/di-mauro21a/di-mauro21a.pdf}, url = {https://proceedings.mlr.press/v161/di-mauro21a.html}, abstract = {Density estimation could be viewed as a core component in machine learning, since a good estimator could be used to solve many tasks such as classification, regression, and imputing missing values. The main challenge of density estimation is balancing the model expressiveness and its learning and inference complexity. Probabilistic circuits (PCs) model a probability distribution as a computational graph. By imposing specific structural properties on such models many inference tasks become tractable. However, learning PCs usually relies on greedy and time consuming procedures. In this paper we propose a new unified approach to efficiently learn PCs having several structural properties. We introduce extremely randomized PCs (XPCs), PCs with a random structure. We show their advantage on standard density estimation benchmarks when compared to other density estimators.} }
Endnote
%0 Conference Paper %T Random probabilistic circuits %A Nicola Di Mauro %A Gennaro Gala %A Marco Iannotta %A Teresa M.A. Basile %B Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2021 %E Cassio de Campos %E Marloes H. Maathuis %F pmlr-v161-di-mauro21a %I PMLR %P 1682--1691 %U https://proceedings.mlr.press/v161/di-mauro21a.html %V 161 %X Density estimation could be viewed as a core component in machine learning, since a good estimator could be used to solve many tasks such as classification, regression, and imputing missing values. The main challenge of density estimation is balancing the model expressiveness and its learning and inference complexity. Probabilistic circuits (PCs) model a probability distribution as a computational graph. By imposing specific structural properties on such models many inference tasks become tractable. However, learning PCs usually relies on greedy and time consuming procedures. In this paper we propose a new unified approach to efficiently learn PCs having several structural properties. We introduce extremely randomized PCs (XPCs), PCs with a random structure. We show their advantage on standard density estimation benchmarks when compared to other density estimators.
APA
Di Mauro, N., Gala, G., Iannotta, M. & Basile, T.M.. (2021). Random probabilistic circuits. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 161:1682-1691 Available from https://proceedings.mlr.press/v161/di-mauro21a.html.

Related Material