Semantic probabilistic layers for neuro-symbolic learning
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 …
any neural network guaranteeing its predictions are consistent with a set of predefined …
Einsum networks: Fast and scalable learning of tractable probabilistic circuits
Probabilistic circuits (PCs) are a promising avenue for probabilistic modeling, as they permit
a wide range of exact and efficient inference routines. Recent “deep-learning-style” …
a wide range of exact and efficient inference routines. Recent “deep-learning-style” …
Continuous mixtures of tractable probabilistic models
Probabilistic models based on continuous latent spaces, such as variational autoencoders,
can be understood as uncountable mixture models where components depend continuously …
can be understood as uncountable mixture models where components depend continuously …
Understanding the distillation process from deep generative models to tractable probabilistic circuits
Abstract Probabilistic Circuits (PCs) are a general and unified computational framework for
tractable probabilistic models that support efficient computation of various inference tasks …
tractable probabilistic models that support efficient computation of various inference tasks …
A survey of sum–product networks structural learning
Sum–product networks (SPNs) in deep probabilistic models have made great progress in
computer vision, robotics, neuro-symbolic artificial intelligence, natural language …
computer vision, robotics, neuro-symbolic artificial intelligence, natural language …
Sum-product networks: A survey
R Sánchez-Cauce, I París… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed
graph, in which terminal nodes represent probability distributions and non-terminal nodes …
graph, in which terminal nodes represent probability distributions and non-terminal nodes …
Sparse probabilistic circuits via pruning and growing
Probabilistic circuits (PCs) are a tractable representation of probability distributions allowing
for exact and efficient computation of likelihoods and marginals. There has been significant …
for exact and efficient computation of likelihoods and marginals. There has been significant …
Interventional sum-product networks: Causal inference with tractable probabilistic models
While probabilistic models are an important tool for studying causality, doing so suffers from
the intractability of inference. As a step towards tractable causal models, we consider the …
the intractability of inference. As a step towards tractable causal models, we consider the …
Group fairness by probabilistic modeling with latent fair decisions
Abstract Machine learning systems are increasingly being used to make impactful decisions
such as loan applications and criminal justice risk assessments, and as such, ensuring …
such as loan applications and criminal justice risk assessments, and as such, ensuring …
Scaling up probabilistic circuits by latent variable distillation
Probabilistic Circuits (PCs) are a unified framework for tractable probabilistic models that
support efficient computation of various probabilistic queries (eg, marginal probabilities) …
support efficient computation of various probabilistic queries (eg, marginal probabilities) …