Publikation
Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning
Robert Peharz; Antonio Vergari; Karl Stelzner; Alejandro Molina; Martin Trapp; Xiaoting Shao; Kristian Kersting; Zoubin Ghahramani
In: Amir Globerson; Ricardo Silva (Hrsg.). Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence. Conference in Uncertainty in Artificial Intelligence (UAI-2019), July 22-25, Tel Aviv, Israel, Pages 334-344, Proceedings of Machine Learning Research, Vol. 115, AUAI Press, 2019.
Zusammenfassung
Sum-product networks (SPNs) are expressive probabilistic models with a rich set of exact and efficient inference routines. However, in order to guarantee exact inference, they require specific structural constraints, which complicate learning SPNs from data. Thereby, most SPN structure learners proposed so far are tedious to tune, do not scale easily, and are not easily integrated with deep learning frameworks. In this paper, we follow a simple “deep learning” approach, by generating unspecialized random structures, scalable to millions of parameters, and subsequently applying GPU-based optimization. Somewhat surprisingly, our models often perform on par with state-of-the-art SPN structure learners and deep neural networks on a diverse range of generative and discriminative scenarios. At the same time, our models yield well-calibrated uncertainties, and stand out among most deep generative and discriminative models in being robust to missing features and being able to detect anomalies.