Score functions

In this section, we would like to introduce score functions in causal-learn. Currently we have BIC score [1], BDeu score [2], generalized score with cross validation or marginal likelihood [3].

Contents:

• BIC score
  • Usage
  • Parameters
  • Returns
• BDeu score
  • Usage
  • Parameters
  • Returns
• Generalized score with cross validation
  • Generalized score with cross validation for single-dimensional variables
  • Generalized score with cross validation for multi-dimensional variables
• Generalized score with marginal likelihood
  • Generalized score with marginal likelihood for single dimensional variables
  • Generalized score with marginal likelihood for multi-dimensional variables

[1]

Schwarz, G. (1978). Estimating the dimension of a model. The annals of statistics, 461-464.

[2]

Buntine, W. (1991). Theory refinement on Bayesian networks. In Uncertainty proceedings 1991 (pp. 52-60). Morgan Kaufmann.

[3]

Huang, B., Zhang, K., Lin, Y., Schölkopf, B., & Glymour, C. (2018, July). Generalized score functions for causal discovery. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 1551-1560).