Skip to yearly menu bar Skip to main content


Probabilistic Integral Circuits

Gennaro Gala · Cassio de Campos · Robert Peharz · Antonio Vergari · Erik Quaeghebeur

MR1 & MR2 - Number 174
[ ]
Thu 2 May 8 a.m. PDT — 8:30 a.m. PDT


Continuous latent variables (LVs) are a key ingredient of many generative models, as they allow modelling expressive mixtures with an uncountable number of components.In contrast, probabilistic circuits (PCs) are hierarchical discrete mixtures represented as computational graphs composed of input, sum and product units.Unlike continuous LV models, PCs provide tractable inference but are limited to discrete LVs with categorical (i.e. unordered) states.We bridge these model classes by introducing probabilistic integral circuits (PICs), a new language of computational graphs that extends PCs with integral units representing continuous LVs.In the first place, PICs are symbolic computational graphs and are fully tractable in simple cases where analytical integration is possible.In practice, we parameterise PICs with light-weight neural nets delivering an intractable hierarchical continuous mixture that can be approximated arbitrarily well with large PCs using numerical quadrature.On several distribution estimation benchmarks, we show that such PIC-approximating PCs systematically outperform PCs commonly learned via expectation-maximization or SGD.

Live content is unavailable. Log in and register to view live content