Normalizing Flows (NFs) are universal density estimators based on Neural Networks. However, this universality is limited: the density's support needs to be diffeomorphic to a Euclidean space. In this paper, we propose a novel method to overcome this limitation without sacrificing universality. The proposed method inflates the data manifold by adding noise in the normal space, trains an NF on this inflated manifold, and, finally, deflates the learned density. Our main result provides sufficient conditions on the manifold and the specific choice of noise under which the corresponding estimator is exact. Our method has the same computational complexity as NFs and does not require computing an inverse flow. We also show that, if the embedding dimension is much larger than the manifold dimension, noise in the normal space can be well approximated by Gaussian noise. This allows using our method for approximating arbitrary densities on unknown manifolds provided that the manifold dimension is known.
翻译:普通化流程(NFs)是基于神经网络的通用密度估计值。 但是,这种普遍性是有限的: 密度支持需要对欧洲culidean 空间进行二进制变异。 在本文中, 我们提出一种新颖的方法来克服这种限制, 同时又不牺牲普遍性。 提议的方法通过在正常空间添加噪音而使数据倍增, 在这种膨胀的多元上培训NF, 最后, 使所学密度减缩。 我们的主要结果为各种元提供了足够的条件, 以及相应的估计值所根据的噪音的具体选择。 我们的方法与 NFs 一样具有计算复杂性, 不需要计算反向流。 我们还表明, 如果嵌入的维度比多得多, 正常空间的噪音可以被高斯噪音非常接近。 这样可以使用我们的方法来适应未知的未知元的任意密度。