Multi-Level Cause-Effect Systems

Krzysztof Chalupka, Frederick Eberhardt, Pietro Perona
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:361-369, 2016.

Abstract

We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et. al. (2015) to the setting in which the macro-level effect is not specified. We formalize the connection between micro- and macro-variables in such situations and provide a coherent framework describing causal relations at multiple levels of analysis. We present an algorithm that discovers macro-variable causes and effects from micro-level measurements obtained from an experiment. We further show how to design experiments to discover macro-variables from observational micro-variable data. Finally, we show that under specific conditions, one can identify multiple levels of causal structure. Throughout the article, we use a simulated neuroscience multi-unit recording experiment to illustrate the ideas and the algorithms.

Cite this Paper


BibTeX
@InProceedings{pmlr-v51-chalupka16, title = {Multi-Level Cause-Effect Systems}, author = {Chalupka, Krzysztof and Eberhardt, Frederick and Perona, Pietro}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics}, pages = {361--369}, year = {2016}, editor = {Gretton, Arthur and Robert, Christian C.}, volume = {51}, series = {Proceedings of Machine Learning Research}, address = {Cadiz, Spain}, month = {09--11 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v51/chalupka16.pdf}, url = {https://proceedings.mlr.press/v51/chalupka16.html}, abstract = {We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et. al. (2015) to the setting in which the macro-level effect is not specified. We formalize the connection between micro- and macro-variables in such situations and provide a coherent framework describing causal relations at multiple levels of analysis. We present an algorithm that discovers macro-variable causes and effects from micro-level measurements obtained from an experiment. We further show how to design experiments to discover macro-variables from observational micro-variable data. Finally, we show that under specific conditions, one can identify multiple levels of causal structure. Throughout the article, we use a simulated neuroscience multi-unit recording experiment to illustrate the ideas and the algorithms.} }
Endnote
%0 Conference Paper %T Multi-Level Cause-Effect Systems %A Krzysztof Chalupka %A Frederick Eberhardt %A Pietro Perona %B Proceedings of the 19th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2016 %E Arthur Gretton %E Christian C. Robert %F pmlr-v51-chalupka16 %I PMLR %P 361--369 %U https://proceedings.mlr.press/v51/chalupka16.html %V 51 %X We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et. al. (2015) to the setting in which the macro-level effect is not specified. We formalize the connection between micro- and macro-variables in such situations and provide a coherent framework describing causal relations at multiple levels of analysis. We present an algorithm that discovers macro-variable causes and effects from micro-level measurements obtained from an experiment. We further show how to design experiments to discover macro-variables from observational micro-variable data. Finally, we show that under specific conditions, one can identify multiple levels of causal structure. Throughout the article, we use a simulated neuroscience multi-unit recording experiment to illustrate the ideas and the algorithms.
RIS
TY - CPAPER TI - Multi-Level Cause-Effect Systems AU - Krzysztof Chalupka AU - Frederick Eberhardt AU - Pietro Perona BT - Proceedings of the 19th International Conference on Artificial Intelligence and Statistics DA - 2016/05/02 ED - Arthur Gretton ED - Christian C. Robert ID - pmlr-v51-chalupka16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 51 SP - 361 EP - 369 L1 - http://proceedings.mlr.press/v51/chalupka16.pdf UR - https://proceedings.mlr.press/v51/chalupka16.html AB - We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et. al. (2015) to the setting in which the macro-level effect is not specified. We formalize the connection between micro- and macro-variables in such situations and provide a coherent framework describing causal relations at multiple levels of analysis. We present an algorithm that discovers macro-variable causes and effects from micro-level measurements obtained from an experiment. We further show how to design experiments to discover macro-variables from observational micro-variable data. Finally, we show that under specific conditions, one can identify multiple levels of causal structure. Throughout the article, we use a simulated neuroscience multi-unit recording experiment to illustrate the ideas and the algorithms. ER -
APA
Chalupka, K., Eberhardt, F. & Perona, P.. (2016). Multi-Level Cause-Effect Systems. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 51:361-369 Available from https://proceedings.mlr.press/v51/chalupka16.html.

Related Material