Removing systematic errors for exoplanet search via latent causes

Bernhard Schölkopf, David Hogg, Dun Wang, Dan Foreman-Mackey, Dominik Janzing, Carl-Johann Simon-Gabriel, Jonas Peters
Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:2218-2226, 2015.

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v37-scholkopf15, title = {Removing systematic errors for exoplanet search via latent causes}, author = {Schölkopf, Bernhard and Hogg, David and Wang, Dun and Foreman-Mackey, Dan and Janzing, Dominik and Simon-Gabriel, Carl-Johann and Peters, Jonas}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning}, pages = {2218--2226}, year = {2015}, editor = {Bach, Francis and Blei, David}, volume = {37}, series = {Proceedings of Machine Learning Research}, address = {Lille, France}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v37/scholkopf15.pdf}, url = {https://proceedings.mlr.press/v37/scholkopf15.html}, 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.} }
Endnote
%0 Conference Paper %T Removing systematic errors for exoplanet search via latent causes %A Bernhard Schölkopf %A David Hogg %A Dun Wang %A Dan Foreman-Mackey %A Dominik Janzing %A Carl-Johann Simon-Gabriel %A Jonas Peters %B Proceedings of the 32nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2015 %E Francis Bach %E David Blei %F pmlr-v37-scholkopf15 %I PMLR %P 2218--2226 %U https://proceedings.mlr.press/v37/scholkopf15.html %V 37 %X 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.
RIS
TY - CPAPER TI - Removing systematic errors for exoplanet search via latent causes AU - Bernhard Schölkopf AU - David Hogg AU - Dun Wang AU - Dan Foreman-Mackey AU - Dominik Janzing AU - Carl-Johann Simon-Gabriel AU - Jonas Peters BT - Proceedings of the 32nd International Conference on Machine Learning DA - 2015/06/01 ED - Francis Bach ED - David Blei ID - pmlr-v37-scholkopf15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 37 SP - 2218 EP - 2226 L1 - http://proceedings.mlr.press/v37/scholkopf15.pdf UR - https://proceedings.mlr.press/v37/scholkopf15.html AB - 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. ER -
APA
Schölkopf, B., Hogg, D., Wang, D., Foreman-Mackey, D., Janzing, D., Simon-Gabriel, C. & Peters, J.. (2015). Removing systematic errors for exoplanet search via latent causes. Proceedings of the 32nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 37:2218-2226 Available from https://proceedings.mlr.press/v37/scholkopf15.html.

Related Material