Fast Causal Division for Supporting High Dimensional Causal Discovery

Discovering the causal relationship from the observational data is a key problem in many scientific research fields. However, it is not easy to discovery the causal relationship by using general causal discovery methods, such as constraint based method or additive noise model, among large scale data, due to the curse of the dimension. Although some causal dividing frameworks are proposed to alleviate this problem, they are, in fact, also faced with high dimensional problems, as the existing causal partitioning frameworks rely on general conditional independence (CI) tests. These methods can deal with very sparse causal graphs, but they often become unreliable, if the causal graphs get more intensive. In this thesis, we propose a splitting and merging strategy to expand the scalability of generalized causal discovery. The segmentation procedure we propose is based on CI tests. Compared with other methods, it returns more reliable results and has strong applicability for various cases.