Conditionally Tractable Density Estimation using Neural Networks

Hailiang Dong, Chiradeep Roy, Tahrima Rahman, Vibhav Gogate, Nicholas Ruozzi
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:6933-6946, 2022.

Abstract

Tractable models such as cutset networks and sum-product networks (SPNs) have become increasingly popular because they have superior predictive performance. Among them, cutset networks, which model the mechanics of Pearl’s cutset conditioning algorithm, demonstrate great scalability and prediction accuracy. Existing research on cutset networks has mainly focused on discrete domains, and the best mechanism to extend cutset networks to continuous domains is unclear. We propose one possible alternative to cutset networks that models the full joint distribution as the product of a local, complex distribution over a small subset of variables and a fully tractable conditional distribution whose parameters are controlled using a neural network. This model admits exact inference when all variables in the local distribution are observed, and although the model is not fully tractable in general, we show that “cutset” sampling can be employed to efficiently generate accurate predictions in practice. We show that our model performs comparably or better than existing competitors through a variety of prediction tasks on real datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v151-dong22a, title = { Conditionally Tractable Density Estimation using Neural Networks }, author = {Dong, Hailiang and Roy, Chiradeep and Rahman, Tahrima and Gogate, Vibhav and Ruozzi, Nicholas}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {6933--6946}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/dong22a/dong22a.pdf}, url = {https://proceedings.mlr.press/v151/dong22a.html}, abstract = { Tractable models such as cutset networks and sum-product networks (SPNs) have become increasingly popular because they have superior predictive performance. Among them, cutset networks, which model the mechanics of Pearl’s cutset conditioning algorithm, demonstrate great scalability and prediction accuracy. Existing research on cutset networks has mainly focused on discrete domains, and the best mechanism to extend cutset networks to continuous domains is unclear. We propose one possible alternative to cutset networks that models the full joint distribution as the product of a local, complex distribution over a small subset of variables and a fully tractable conditional distribution whose parameters are controlled using a neural network. This model admits exact inference when all variables in the local distribution are observed, and although the model is not fully tractable in general, we show that “cutset” sampling can be employed to efficiently generate accurate predictions in practice. We show that our model performs comparably or better than existing competitors through a variety of prediction tasks on real datasets. } }
Endnote
%0 Conference Paper %T Conditionally Tractable Density Estimation using Neural Networks %A Hailiang Dong %A Chiradeep Roy %A Tahrima Rahman %A Vibhav Gogate %A Nicholas Ruozzi %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-dong22a %I PMLR %P 6933--6946 %U https://proceedings.mlr.press/v151/dong22a.html %V 151 %X Tractable models such as cutset networks and sum-product networks (SPNs) have become increasingly popular because they have superior predictive performance. Among them, cutset networks, which model the mechanics of Pearl’s cutset conditioning algorithm, demonstrate great scalability and prediction accuracy. Existing research on cutset networks has mainly focused on discrete domains, and the best mechanism to extend cutset networks to continuous domains is unclear. We propose one possible alternative to cutset networks that models the full joint distribution as the product of a local, complex distribution over a small subset of variables and a fully tractable conditional distribution whose parameters are controlled using a neural network. This model admits exact inference when all variables in the local distribution are observed, and although the model is not fully tractable in general, we show that “cutset” sampling can be employed to efficiently generate accurate predictions in practice. We show that our model performs comparably or better than existing competitors through a variety of prediction tasks on real datasets.
APA
Dong, H., Roy, C., Rahman, T., Gogate, V. & Ruozzi, N.. (2022). Conditionally Tractable Density Estimation using Neural Networks . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:6933-6946 Available from https://proceedings.mlr.press/v151/dong22a.html.

Related Material