− | 由于<math>W</math>可以通过<math>X</math>直接数据披露产生,故可以定义,<math>W</math>对于<math>X</math>有马尔可夫依赖。由于<math>Y</math>是从数据集<math>X</math>中变化产生,故<math>Y</math>对<math>X</math>也存在马尔可夫依赖。因此可以用,<math>p_{W|X}</math>和<math>p_{Y|X}</math>两个条件表示<math>W</math>对<math>X</math>,<math>Y</math>对<math>X</math>的映射关系。这样<math>W-X-Y</math>就可以构成一条马尔科夫链。<ref name=":0">Rassouli, B. , Rosas, F. E. , & Gunduz, D. . (2019). Data disclosure under perfect sample privacy. IEEE Transactions on Information Forensics and Security, PP(99), 1-1. </ref><ref name=":2">Rosas FE, Mediano PAM, Jensen HJ, Seth AK, Barrett AB, Carhart-Harris RL, et al. (2020) Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data. PLoS Comput Biol 16(12): e1008289.</ref>
| + | </math>的整个流形<math>p(\mathbf{y}|\mathbf{x}) |