论文标题
基于流量的生成建模的一般可逆转换
General Invertible Transformations for Flow-based Generative Modeling
论文作者
论文摘要
在本文中，我们提出了一类新的可逆转换，并应用于基于流的生成模型。我们指出，可逆逻辑和可逆神经网络中许多众所周知的可逆转变可能源自我们的命题。接下来，我们提出了两个新的耦合层，这些耦合层是基于流量的生成模型的重要组成部分。在数字数据的实验中，我们介绍了如何在整数离散流（IDF）中使用这些新耦合层，并且它们比IDF和RealnVP中使用的标准耦合层获得更好的结果。
In this paper, we present a new class of invertible transformations with an application to flow-based generative models. We indicate that many well-known invertible transformations in reversible logic and reversible neural networks could be derived from our proposition. Next, we propose two new coupling layers that are important building blocks of flow-based generative models. In the experiments on digit data, we present how these new coupling layers could be used in Integer Discrete Flows (IDF), and that they achieve better results than standard coupling layers used in IDF and RealNVP.
