论文标题
流量的流量：训练在任意分布之间的归一流流量，并具有最大似然估计
Flows for Flows: Training Normalizing Flows Between Arbitrary Distributions with Maximum Likelihood Estimation
论文作者
论文摘要
归一化流是由具有已知密度和具有可聊天雅各布式的差异的基础分布构建的。归一流流的基本密度可以通过不同的归一流流量来参数，从而可以在任意分布之间找到地图。我们演示和探索了这种方法的实用性，并表明在有条件地标准化流量并在使用归一化流量构建的地图上引入最佳传输约束的情况下，它特别有趣。
Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian. The base density of a normalizing flow can be parameterised by a different normalizing flow, thus allowing maps to be found between arbitrary distributions. We demonstrate and explore the utility of this approach and show it is particularly interesting in the case of conditional normalizing flows and for introducing optimal transport constraints on maps that are constructed using normalizing flows.
