BriefGPT.xyz
Apr, 2020
Einsum Networks: 可计算概率电路的快速可扩展学习
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
HTML
PDF
Robert Peharz, Steven Lang, Antonio Vergari, Karl Stelzner, Alejandro Molina...
TL;DR
本文提出了基于Einsum Networks的概率电路模型实现,通过简化Expectation-Maximization算法的实现以及在数据集上的应用来提高其可扩展性,并且作为一种忠实的生成图像模型。
Abstract
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'' implementations of PCs strive for a better
→