arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.12335cs.LGstat.ML
收藏

因果学习中的循环

Cycles in Causal Learning

Google Research(谷歌研究院)

Katie Everett, Ian Fischer

摘要:

在因果学习中,我们希望学习变量之间的因果关系,以便我们能够正确地推断干预的效果。虽然循环结构和非循环结构之间的差异可能只是一条边,但循环因果结构在干预下具有质的不同行为:当干预的下游效应传播回源变量时,循环会导致反馈回路。我们提出了三个理论观察概率分布与自指因子分解,即分布,可以用图形表示的一个周期。首先,我们证明了两个变量的自指分布实际上是独立的。其次,我们证明了N个变量的自参考分布具有零互信息。最后,我们证明了自指分布,因式分解在一个周期,也因式分解,好像周期被逆转。这些结果表明,即使观测数据表明变量之间的独立性,也可能存在循环因果依赖。基于估计互信息的方法,或基于独立因果机制的推理,很可能无法学习循环因果结构。我们鼓励未来的工作在因果学习,仔细考虑周期。

英文摘要:

In the causal learning setting, we wish to learn cause-and-effect relationships between variables such that we can correctly infer the effect of an intervention. While the difference between a cyclic structure and an acyclic structure may be just a single edge, cyclic causal structures have qualitatively different behavior under intervention: cycles cause feedback loops when the downstream effect of an intervention propagates back to the source variable. We present three theoretical observations about probability distributions with self-referential factorizations, i.e. distributions that could be graphically represented with a cycle. First, we prove that self-referential distributions in two variables are, in fact, independent. Second, we prove that self-referential distributions in N variables have zero mutual information. Lastly, we prove that self-referential distributions that factorize in a cycle, also factorize as though the cycle were reversed. These results suggest that cyclic causal dependence may exist even where observational data suggest independence among variables. Methods based on estimating mutual information, or heuristics based on independent causal mechanisms, are likely to fail to learn cyclic casual structures. We encourage future work in causal learning that carefully considers cycles.

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。

↑