Causal Discovery as a Game

Frederick Eberhardt
; Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008, PMLR 6:87-96, 2010.

Abstract

This paper presents a game theoretic approach to causal discovery. The problem of causal discovery is framed as a game of the Scientist against Nature, in which Nature attempts to hide its secrets for as long as possible, and the Scientist makes her best effort at discovery while minimizing cost. This approach provides a very general framework for the assessment of different search procedures and a principled way of modeling the effect of choices between different experiments.

Cite this Paper


BibTeX
@InProceedings{pmlr-v6-eberhardt10a, title = {Causal Discovery as a Game}, author = {Frederick Eberhardt}, booktitle = {Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008}, pages = {87--96}, year = {2010}, editor = {Isabelle Guyon and Dominik Janzing and Bernhard Schölkopf}, volume = {6}, series = {Proceedings of Machine Learning Research}, address = {Whistler, Canada}, month = {12 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v6/eberhardt10a/eberhardt10a.pdf}, url = {http://proceedings.mlr.press/v6/eberhardt10a.html}, abstract = {This paper presents a game theoretic approach to causal discovery. The problem of causal discovery is framed as a game of the Scientist against Nature, in which Nature attempts to hide its secrets for as long as possible, and the Scientist makes her best effort at discovery while minimizing cost. This approach provides a very general framework for the assessment of different search procedures and a principled way of modeling the effect of choices between different experiments.} }
Endnote
%0 Conference Paper %T Causal Discovery as a Game %A Frederick Eberhardt %B Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008 %C Proceedings of Machine Learning Research %D 2010 %E Isabelle Guyon %E Dominik Janzing %E Bernhard Schölkopf %F pmlr-v6-eberhardt10a %I PMLR %J Proceedings of Machine Learning Research %P 87--96 %U http://proceedings.mlr.press %V 6 %W PMLR %X This paper presents a game theoretic approach to causal discovery. The problem of causal discovery is framed as a game of the Scientist against Nature, in which Nature attempts to hide its secrets for as long as possible, and the Scientist makes her best effort at discovery while minimizing cost. This approach provides a very general framework for the assessment of different search procedures and a principled way of modeling the effect of choices between different experiments.
RIS
TY - CPAPER TI - Causal Discovery as a Game AU - Frederick Eberhardt BT - Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008 PY - 2010/02/18 DA - 2010/02/18 ED - Isabelle Guyon ED - Dominik Janzing ED - Bernhard Schölkopf ID - pmlr-v6-eberhardt10a PB - PMLR SP - 87 DP - PMLR EP - 96 L1 - http://proceedings.mlr.press/v6/eberhardt10a/eberhardt10a.pdf UR - http://proceedings.mlr.press/v6/eberhardt10a.html AB - This paper presents a game theoretic approach to causal discovery. The problem of causal discovery is framed as a game of the Scientist against Nature, in which Nature attempts to hide its secrets for as long as possible, and the Scientist makes her best effort at discovery while minimizing cost. This approach provides a very general framework for the assessment of different search procedures and a principled way of modeling the effect of choices between different experiments. ER -
APA
Eberhardt, F.. (2010). Causal Discovery as a Game. Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008, in PMLR 6:87-96

Related Material