用于密度估计的三角形网络
A Triangular Network For Density Estimation
摘要:
我们报告了一个三角形神经网络实现的神经自回归流(NAF)。与许多通用的自回归密度模型不同,我们的设计是高度模块化的,参数经济,计算效率高,适用于高维度数据的密度估计。它实现了最先进的每维比特指数MNIST和CIFAR-10(约1.1和3.7,分别)的类别中的通用密度估计。
英文摘要:
We report a triangular neural network implementation of neural autoregressive flow (NAF). Unlike many universal autoregressive density models, our design is highly modular, parameter economy, computationally efficient, and applicable to density estimation of data with high dimensions. It achieves state-of-the-art bits-per-dimension indices on MNIST and CIFAR-10 (about 1.1 and 3.7, respectively) in the category of general-purpose density estimators.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。