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 2205.10083cs.LGcs.AI
收藏

一种面向循环与非循环因果模型的统一实验设计方法

A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models

EPFL(洛桑联邦理工学院);Leiden University(莱顿大学);Boston University(波士顿大学)

Ehsan Mokhtarian, Saber Salehkaleybar, AmirEmad Ghassami, Negar Kiyavash

AI总结:

针对循环因果图实验设计的难点,提出统一适用于循环与非循环因果模型的实验设计方法,证明其在实验次数和受限实验规模下均达到最优性。

摘要:

我们研究用于唯一识别简单结构因果模型(SCM)因果图的实验设计问题,该因果图可能包含循环。结构中循环的存在给实验设计带来了重大挑战:与非循环图不同,仅靠观测分布可能无法学习带环因果图的骨架。此外,对此类图中的变量进行干预,并不一定能确定与该变量相连的所有边的方向。本文提出一种实验设计方法,既能学习循环图也能学习非循环图,从而统一了两类图的实验设计任务。我们给出了最坏情况下保证因果图唯一识别所需实验次数的下界,证明所提方法在实验次数上是阶最优的,差距仅为一个加性对数项。此外,我们将结果扩展到每次实验的规模受常数限制的场景。针对该场景,我们证明在最坏情况下唯一识别因果图所需的最大实验规模方面,我们的方法是最优的。

英文摘要:

We study experiment design for unique identification of the causal graph of a simple SCM, where the graph may contain cycles. The presence of cycles in the structure introduces major challenges for experiment design as, unlike acyclic graphs, learning the skeleton of causal graphs with cycles may not be possible from merely the observational distribution. Furthermore, intervening on a variable in such graphs does not necessarily lead to orienting all the edges incident to it. In this paper, we propose an experiment design approach that can learn both cyclic and acyclic graphs and hence, unifies the task of experiment design for both types of graphs. We provide a lower bound on the number of experiments required to guarantee the unique identification of the causal graph in the worst case, showing that the proposed approach is order-optimal in terms of the number of experiments up to an additive logarithmic term. Moreover, we extend our result to the setting where the size of each experiment is bounded by a constant. For this case, we show that our approach is optimal in terms of the size of the largest experiment required for uniquely identifying the causal graph in the worst case.

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。

↑