arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.09054stat.MLcs.AIcs.LG
收藏

论因果位置-尺度噪声模型的可辨识性与估计

On the Identifiability and Estimation of Causal Location-Scale Noise Models

ETH Zurich(苏黎世联邦理工学院);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Alexander Immer, Christoph Schultheiss, Julia E. Vogt, Bernhard Schölkopf, Peter Bühlmann, Alexander Marx

AI总结:

本文研究异方差位置-尺度噪声模型的因果方向可辨识性,提出基于特征映射与神经网络的两类估计器,并证明前者的联合凹性与一致性,后者在基准上达到最优性能。

摘要:

我们研究位置-尺度或异方差噪声模型(LSNMs)这一类别,其中结果 Y 可以表示为原因 X 与独立于 X 的噪声源 N 的函数,且该噪声源可由关于原因的正函数 g 缩放,即 Y = f(X) + g(X)N。尽管该模型类别具有一般性,我们仍证明因果方向在除某些病态情形外是可辨识的。为从经验上验证这些理论发现,我们提出两种用于 LSNM 的估计器:一种基于(非线性)特征映射,另一种基于神经网络。二者均将给定 X 时 Y 的条件分布建模为由其自然参数参数化的高斯分布。当特征映射被正确指定时,我们证明所提估计器是联合凹的,并且是因果辨识任务的一致估计器。虽然神经网络估计器不继承这些保证,但它能够拟合任意复杂度的函数,并在各基准测试中达到最先进性能。

英文摘要:

We study the class of location-scale or heteroscedastic noise models (LSNMs), in which the effect $Y$ can be written as a function of the cause $X$ and a noise source $N$ independent of $X$, which may be scaled by a positive function $g$ over the cause, i.e., $Y = f(X) + g(X)N$. Despite the generality of the model class, we show the causal direction is identifiable up to some pathological cases. To empirically validate these theoretical findings, we propose two estimators for LSNMs: an estimator based on (non-linear) feature maps, and one based on neural networks. Both model the conditional distribution of $Y$ given $X$ as a Gaussian parameterized by its natural parameters. When the feature maps are correctly specified, we prove that our estimator is jointly concave, and a consistent estimator for the cause-effect identification task. Although the the neural network does not inherit those guarantees, it can fit functions of arbitrary complexity, and reaches state-of-the-art performance across benchmarks.

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。

↑