arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.03095cs.LG
收藏

基于规则的规范化流因果结构学习

Gradient-based Causal Structure Learning with Normalizing Flow

University of Adelaide(阿德莱德大学);School of Computer Science(计算机科学学院)

Xiongren Chen

摘要:

在本文中,我们提出了一种基于分数的归一化流方法DAG-NF来学习输入观测数据的依赖关系。受计算机视觉中Grad-CAM的启发,我们使用输出对输入的雅可比矩阵作为因果关系,并且该方法可以推广到任何神经网络,特别是对于基于流的生成神经网络,例如掩蔽自回归流(MAF)和连续归一化流(CNF),其计算输入数据和目标分布的对数似然损失和分布的发散。该方法扩展了NOTEARS算法,对图的连续邻接矩阵施加了重要的酰基性约束,大大降低了图的搜索空间的计算复杂性。

英文摘要:

In this paper, we propose a score-based normalizing flow method called DAG-NF to learn dependencies of input observation data. Inspired by Grad-CAM in computer vision, we use jacobian matrix of output on input as causal relationships and this method can be generalized to any neural networks especially for flow-based generative neural networks such as Masked Autoregressive Flow(MAF) and Continuous Normalizing Flow(CNF) which compute the log likelihood loss and divergence of distribution of input data and target distribution. This method extends NOTEARS which enforces a important acylicity constraint on continuous adjacency matrix of graph nodes and significantly reduce the computational complexity of search space of graph.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑