论文标题
同时流动学习和密度估计的流量
Flows for simultaneous manifold learning and density estimation
论文作者
论文摘要
我们介绍了歧管学习流（M-Flows），这是一种新的生成模型类别，同时了解该歧管上的数据歧管以及可处理的概率密度。结合标准化流，gan，自动编码器和基于能量的模型的各个方面，它们有可能更忠实地代表具有多种结构的数据集，并提供降低维度，去索和分布外检测的手柄。我们认为为什么不应该单独使用最大可能性来训练此类模型，并提出一种新的培训算法，该算法将多种变化和密度更新分开。在一系列实验中，我们演示了M-Flows如何学习数据歧管并允许比环境数据空间中的标准流更好推理。
We introduce manifold-learning flows (M-flows), a new class of generative models that simultaneously learn the data manifold as well as a tractable probability density on that manifold. Combining aspects of normalizing flows, GANs, autoencoders, and energy-based models, they have the potential to represent datasets with a manifold structure more faithfully and provide handles on dimensionality reduction, denoising, and out-of-distribution detection. We argue why such models should not be trained by maximum likelihood alone and present a new training algorithm that separates manifold and density updates. In a range of experiments we demonstrate how M-flows learn the data manifold and allow for better inference than standard flows in the ambient data space.
