Skip to main content Skip to main navigation


Probabilistic Flow Circuits: Towards Unified Deep Models for Tractable Probabilistic Inference

Sahil Sidheekh; Kristian Kersting; Sriraam Natarajan
In: Robin J. Evans; Ilya Shpitser (Hrsg.). Uncertainty in Artificial Intelligence. Conference in Uncertainty in Artificial Intelligence (UAI), July 31 - August 4, Pittsburgh, PA, USA, Pages 1964-1973, Proceedings of Machine Learning Research, Vol. 216, PMLR, 2023.


We consider the problem of increasing the expressivity of probabilistic circuits by augmenting them with the successful generative models of normalizing flows. To this effect, we theoretically establish the requirement of decomposability for such combinations to retain tractability of the learned models. Our model, called Probabilistic Flow Circuits, essentially extends circuits by allowing for normalizing flows at the leaves. Our empirical evaluation clearly establishes the expressivity and tractability of this new class of probabilistic circuits.

Weitere Links