Causal screening in dynamical systems

Søren Wengel Mogensen
Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), PMLR 124:310-319, 2020.

Abstract

Many classical algorithms output graphical representations of causal structures by testing conditional independence among a set of random variables. In dynamical systems, local independence can be used analogously as a testable implication of the underlying data-generating process. We suggest some inexpensive methods for causal screening which provide output with a sound causal interpretation under the assumption of ancestral faithfulness. The popular model class of linear Hawkes processes is used to provide an example of a dynamical causal model. We argue that for sparse causal graphs the output will often be close to complete. We give examples of this framework and apply it to a challenging biological system.

Cite this Paper

BibTeX
@InProceedings{pmlr-v124-wengel-mogensen20a, title = {Causal screening in dynamical systems}, author = {Wengel Mogensen, S\o{}ren}, booktitle = {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)}, pages = {310--319}, year = {2020}, editor = {Peters, Jonas and Sontag, David}, volume = {124}, series = {Proceedings of Machine Learning Research}, month = {03--06 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v124/wengel-mogensen20a/wengel-mogensen20a.pdf}, url = {https://proceedings.mlr.press/v124/wengel-mogensen20a.html}, abstract = {Many classical algorithms output graphical representations of causal structures by testing conditional independence among a set of random variables. In dynamical systems, local independence can be used analogously as a testable implication of the underlying data-generating process. We suggest some inexpensive methods for causal screening which provide output with a sound causal interpretation under the assumption of ancestral faithfulness. The popular model class of linear Hawkes processes is used to provide an example of a dynamical causal model. We argue that for sparse causal graphs the output will often be close to complete. We give examples of this framework and apply it to a challenging biological system.} }
Endnote
%0 Conference Paper %T Causal screening in dynamical systems %A Søren Wengel Mogensen %B Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI) %C Proceedings of Machine Learning Research %D 2020 %E Jonas Peters %E David Sontag %F pmlr-v124-wengel-mogensen20a %I PMLR %P 310--319 %U https://proceedings.mlr.press/v124/wengel-mogensen20a.html %V 124 %X Many classical algorithms output graphical representations of causal structures by testing conditional independence among a set of random variables. In dynamical systems, local independence can be used analogously as a testable implication of the underlying data-generating process. We suggest some inexpensive methods for causal screening which provide output with a sound causal interpretation under the assumption of ancestral faithfulness. The popular model class of linear Hawkes processes is used to provide an example of a dynamical causal model. We argue that for sparse causal graphs the output will often be close to complete. We give examples of this framework and apply it to a challenging biological system.
APA
Wengel Mogensen, S.. (2020). Causal screening in dynamical systems. Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), in Proceedings of Machine Learning Research 124:310-319 Available from https://proceedings.mlr.press/v124/wengel-mogensen20a.html.

Related Material