作者：
摘要：
A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network.
一类比较靠谱的生成式模型通过可逆神经网络将数据点从一个简单的分布映射到一个复杂的分布。
Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants.
这些模型的训练基于似然函数，因此，他们的架构必须能够保证高效地计算 Jacobian 行列式。
Alternatively, the Jacobian trace can be used if the transformation is specified by an ordinary differential equation.
或者，Jacobian 迹在转换由一个常微分方程指定时可被使用。
In this paper, we use Hutchinson's trace estimator to give a scalable unbiased estimate of the log-density.
这项工作使用了 Hutchinson 迹估计器来给出对数密度函数的可规模化无偏估计
The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures.
最终得出一个有着无偏密度估计和单趟采样但保证无严格限制神经网络架构的连续时间可逆生成式模型
We demonstrate our approach on high-dimensional density estimation, image generation, and variational inference, achieving the state-of-the-art among exact likelihood methods with efficient sampling.
本方法在高维密度估计、图像生成和变分推断中，在有高效采样的精确似然方法中达到了目前最佳水平
网友评论