Name
Abstract | ||
|---|---|---|
The discovery of causal relationships between a set of observed variables is a fun- damental problem in science. For continuous-valued data linear acyclic causal models with additive noise are often used because these models are well under- stood and there are well-known methods to fit them to data. In reality, of course, many causal relationships are more or less nonlinear, raising some doubts as to the applicability and usefulness of purely linear methods. In this contribution we show that the basic linear framework can be generalized to nonlinear models. In this extended framework, nonlinearities in the data-generating process are in fact a blessing rather than a curse, as they typically provide information on the underly- ing causal system and allow more aspects of the true data-generating mechanisms to be identified. In addition to theoretical results we show simulations and some simple real data experiments illustrating the identification power provided by non- linearities. |
Year | Venue | Keywords |
|---|---|---|
2008 | NIPS | causal models |
Field | DocType | Citations |
Linear methods,Nonlinear system,Computer science,Acyclic model,Curse,Artificial intelligence,Causal system,Machine learning,Causal model | Conference | 137 |
PageRank | References | Authors |
6.88 | 9 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| patrik o hoyer | 1 | 2040 | 173.13 |
| Dominik Janzing | 2 | 723 | 65.30 |
| Joris M. Mooij | 3 | 679 | 50.48 |
| Jonas Peters | 4 | 505 | 31.25 |
| Bernhard Schölkopf | 5 | 23120 | 3091.82 |