论文标题
对因果模型的适应速度的分析
An Analysis of the Adaptation Speed of Causal Models
论文作者
论文摘要
考虑未知干预措施在未知结构性因果模型$ g $上产生的数据集的集合。最近，Bengio等。 （2020）推测，在所有候选模型中，$ g $是从一个数据集适应另一个数据集的最快，以及有希望的实验。的确，直觉上$ g $的适应机制较少，但是这种理由是不完整的。我们的贡献是对这一假设的更全面分析。我们研究了原因效应SCM的适应速度。使用随机优化的收敛速率，我们证明适应速度的相关代理是干预后参数空间中的距离。将此代理应用于分类和正常原因效应模型，我们显示了两个结果。当干预措施在原因变量上时，具有正确因果方向的SCM会受到很大的因素的优势。当干预措施在效应变量上时，我们表征相对适应速度。令人惊讶的是，我们发现抗泡沫模型优势的情况，可以伪造初始假设。可以在https://github.com/remilepriol/causal-apaptation-peed上获得复制实验的代码
Consider a collection of datasets generated by unknown interventions on an unknown structural causal model $G$. Recently, Bengio et al. (2020) conjectured that among all candidate models, $G$ is the fastest to adapt from one dataset to another, along with promising experiments. Indeed, intuitively $G$ has less mechanisms to adapt, but this justification is incomplete. Our contribution is a more thorough analysis of this hypothesis. We investigate the adaptation speed of cause-effect SCMs. Using convergence rates from stochastic optimization, we justify that a relevant proxy for adaptation speed is distance in parameter space after intervention. Applying this proxy to categorical and normal cause-effect models, we show two results. When the intervention is on the cause variable, the SCM with the correct causal direction is advantaged by a large factor. When the intervention is on the effect variable, we characterize the relative adaptation speed. Surprisingly, we find situations where the anticausal model is advantaged, falsifying the initial hypothesis. Code to reproduce experiments is available at https://github.com/remilepriol/causal-adaptation-speed
