论文标题
图形残差流
Graphical Residual Flows
论文作者
论文摘要
图形流程通过编码非平凡的变量依赖性来增加归一流的结构。以前的图形流模型主要集中在单个流动方向上：密度估计的归一化方向或推理的生成方向。但是，要使用单个流以两个方向执行任务，该模型必须表现出稳定且有效的流动反转。这项工作引入了图形残差流，这是基于可逆残差网络的图形流。我们将依赖信息纳入流中的方法意味着我们能够准确计算这些流量的雅各布决定因素。我们的实验证实，图形残差流提供稳定，准确的反转，这比具有相似任务性能的替代流动也更具时间效率。此外，我们的模型提供了具有密度估计和推理任务的其他图形流量的性能竞争。
Graphical flows add further structure to normalizing flows by encoding non-trivial variable dependencies. Previous graphical flow models have focused primarily on a single flow direction: the normalizing direction for density estimation, or the generative direction for inference. However, to use a single flow to perform tasks in both directions, the model must exhibit stable and efficient flow inversion. This work introduces graphical residual flows, a graphical flow based on invertible residual networks. Our approach to incorporating dependency information in the flow, means that we are able to calculate the Jacobian determinant of these flows exactly. Our experiments confirm that graphical residual flows provide stable and accurate inversion that is also more time-efficient than alternative flows with similar task performance. Furthermore, our model provides performance competitive with other graphical flows for both density estimation and inference tasks.
