Probabilistic Neural Circuits

arXiv:2403.06235v1 Announce Type: new
Abstract: Probabilistic circuits (PCs) have gained prominence in recent years as a versatile framework for discussing probabilistic models that support tractable queries and are yet expressive enough to model complex probability distributions. Nevertheless, tractability comes at a cost: PCs are less expressive than neural networks. In this paper we introduce probabilistic neural circuits (PNCs), which strike a balance between PCs and neural nets in terms of tractability and expressive power. Theoretically, we show that PNCs can …

abstract arxiv cost cs.ai cs.lg cs.ne framework networks neural networks paper pcs probability queries stat.ml support tractable type