2024-09-12-dong24b.md

title	abstract	openreview	software	section	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Learning Distributionally Robust Tractable Probabilistic Models in Continuous Domains	Tractable probabilistic models (TPMs) have attracted substantial research interest in recent years, particularly because of their ability to answer various reasoning queries in polynomial time. In this study, we focus on the distributionally robust learning of continuous TPMs and address the challenge of distribution shift at test time by tackling the adversarial risk minimization problem within the framework of distributionally robust learning. Specifically, we demonstrate that the adversarial risk minimization problem can be efficiently addressed when the model permits exact log-likelihood evaluation and efficient learning on weighted data. Our experimental results on several real-world datasets show that our approach achieves significantly higher log-likelihoods on adversarial test sets. Remarkably, we note that the model learned via distributionally robust learning can achieve higher average log-likelihood on the initial uncorrupted test set at times.	SlxO1NpLiE	https://github.com/LeonDong1993/UAI2024-RobustLearning	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	dong24b	0	Learning Distributionally Robust Tractable Probabilistic Models in Continuous Domains	1176	1188	1176-1188	1176	false	Dong, Hailiang and Amato, James and Gogate, Vibhav and Ruozzi, Nicholas	given family Hailiang Dong given family James Amato given family Vibhav Gogate given family Nicholas Ruozzi	2024-09-12		Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence	244	inproceedings	date-parts 2024 9 12	https://raw.githubusercontent.com/mlresearch/v244/main/assets/dong24b/dong24b.pdf