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

Sahil Sidheekh, Kristian Kersting, Sriraam Natarajan

Keywords: probabilistic circuits, tractable generative models, normalizing flows, einsum networks, probabilistic generative models

TL;DR: A principled approach to building expressive and tractable generative models by integrating normalizing flows with probabilistic circuits.

Abstract: 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.