English

Removing systematic errors for exoplanet search via latent causes

Machine Learning 2015-05-13 v1 Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics Machine Learning

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.

Keywords

Cite

@article{arxiv.1505.03036,
  title  = {Removing systematic errors for exoplanet search via latent causes},
  author = {Bernhard Schölkopf and David W. Hogg and Dun Wang and Daniel Foreman-Mackey and Dominik Janzing and Carl-Johann Simon-Gabriel and Jonas Peters},
  journal= {arXiv preprint arXiv:1505.03036},
  year   = {2015}
}

Comments

Extended version of a paper appearing in the Proceedings of the 32nd International Conference on Machine Learning, Lille, France, 2015

R2 v1 2026-06-22T09:32:45.359Z