Abstract | ||
---|---|---|
We describe a method for removing the effect of confounders in order to reconstruct a latent quantity of interest. The method, referred to as half-sibling regression, is inspired by recent work in causal inference using additive noise models. We provide a theoretical justification and illustrate the potential of the method in a challenging astronomy application. |
Year | Venue | Field |
---|---|---|
2015 | International Conference on Machine Learning | Causal inference,Systematic error,Regression,Artificial intelligence,Exoplanet,Mathematics,Machine learning |
DocType | Volume | Citations |
Journal | abs/1505.03036 | 0 |
PageRank | References | Authors |
0.34 | 4 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bernhard Schölkopf | 1 | 23120 | 3091.82 |
David W. Hogg | 2 | 44 | 4.55 |
dun wang | 3 | 0 | 1.35 |
Daniel Foreman-Mackey | 4 | 0 | 1.01 |
Dominik Janzing | 5 | 723 | 65.30 |
Carl-Johann Simon-Gabriel | 6 | 37 | 3.61 |
Jonas Peters | 7 | 505 | 31.25 |