We design a predictive layer for structured-output prediction (SOP) that can be plugged into
any neural network guaranteeing its predictions are consistent with a set of predefined …

This paper develops a novel methodology to simultaneously learn a neural network and
extract generalized logic rules. Different from prior neural-symbolic methods that require …

Probabilistic models based on continuous latent spaces, such as variational autoencoders,
can be understood as uncountable mixture models where components depend continuously …

Abstract Probabilistic Circuits (PCs) are a general and unified computational framework for
tractable probabilistic models that support efficient computation of various inference tasks …

Probabilistic circuits (PCs) are a tractable representation of probability distributions allowing
for exact and efficient computation of likelihoods and marginals. There has been significant …

Probabilistic Circuits (PCs) are a unified framework for tractable probabilistic models that
support efficient computation of various probabilistic queries (eg, marginal probabilities) …

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 …

Despite extensive progress on image generation, common deep generative model
architectures are not easily applied to lossless compression. For example, VAEs suffer from …

This paper establishes a rigorous connection between circuit representations and tensor
factorizations, two seemingly distinct yet fundamentally related areas. By connecting these …

Probabilistic circuits (PCs) are a family of generative models which allows for the
computation of exact likelihoods and marginals of its probability distributions. PCs are both …