arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.05739cs.LG
收藏

技术报告:使用全协方差矩阵训练混合密度网络

Technical report: Training Mixture Density Networks with full covariance matrices

Heidelberg University(海德堡大学)

Jakob Kruse

摘要:

混合密度网络是一个久经考验的工具,用于建模条件概率分布。因此,它们构成了解决这个问题的新方法的一个很好的基线。在标准公式中,MDN采用高斯混合模型的一些输入和输出参数,并对混合分量的协方差进行限制。由于随机变量之间的协方差是我们正在研究的条件建模问题中的一个核心问题,我推导并实现了一个具有无限制协方差的MDN公式。这可能是以前做过的,但我在网上找不到任何资源。出于这个原因,我以本技术报告的形式记录了我的方法,希望它可能对面临类似情况的其他人有用。

英文摘要:

Mixture Density Networks are a tried and tested tool for modelling conditional probability distributions. As such, they constitute a great baseline for novel approaches to this problem. In the standard formulation, an MDN takes some input and outputs parameters for a Gaussian mixture model with restrictions on the mixture components' covariance. Since covariance between random variables is a central issue in the conditional modeling problems we were investigating, I derived and implemented an MDN formulation with unrestricted covariances. It is likely that this has been done before, but I could not find any resources online. For this reason, I have documented my approach in the form of this technical report, in hopes that it may be useful to others facing a similar situation.

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。

↑