Operationalizing Complex Causes: A Pragmatic View of Mediation

Limor Gultchin, David Watson, Matt Kusner, Ricardo Silva
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3875-3885, 2021.

Abstract

We examine the problem of causal response estimation for complex objects (e.g., text, images, genomics). In this setting, classical \emph{atomic} interventions are often not available (e.g., changes to characters, pixels, DNA base-pairs). Instead, we only have access to indirect or \emph{crude} interventions (e.g., enrolling in a writing program, modifying a scene, applying a gene therapy). In this work, we formalize this problem and provide an initial solution. Given a collection of candidate mediators, we propose (a) a two-step method for predicting the causal responses of crude interventions; and (b) a testing procedure to identify mediators of crude interventions. We demonstrate, on a range of simulated and real-world-inspired examples, that our approach allows us to efficiently estimate the effect of crude interventions with limited data from new treatment regimes.

Cite this Paper


BibTeX
@InProceedings{pmlr-v139-gultchin21a, title = {Operationalizing Complex Causes: A Pragmatic View of Mediation}, author = {Gultchin, Limor and Watson, David and Kusner, Matt and Silva, Ricardo}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {3875--3885}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/gultchin21a/gultchin21a.pdf}, url = {https://proceedings.mlr.press/v139/gultchin21a.html}, abstract = {We examine the problem of causal response estimation for complex objects (e.g., text, images, genomics). In this setting, classical \emph{atomic} interventions are often not available (e.g., changes to characters, pixels, DNA base-pairs). Instead, we only have access to indirect or \emph{crude} interventions (e.g., enrolling in a writing program, modifying a scene, applying a gene therapy). In this work, we formalize this problem and provide an initial solution. Given a collection of candidate mediators, we propose (a) a two-step method for predicting the causal responses of crude interventions; and (b) a testing procedure to identify mediators of crude interventions. We demonstrate, on a range of simulated and real-world-inspired examples, that our approach allows us to efficiently estimate the effect of crude interventions with limited data from new treatment regimes.} }
Endnote
%0 Conference Paper %T Operationalizing Complex Causes: A Pragmatic View of Mediation %A Limor Gultchin %A David Watson %A Matt Kusner %A Ricardo Silva %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-gultchin21a %I PMLR %P 3875--3885 %U https://proceedings.mlr.press/v139/gultchin21a.html %V 139 %X We examine the problem of causal response estimation for complex objects (e.g., text, images, genomics). In this setting, classical \emph{atomic} interventions are often not available (e.g., changes to characters, pixels, DNA base-pairs). Instead, we only have access to indirect or \emph{crude} interventions (e.g., enrolling in a writing program, modifying a scene, applying a gene therapy). In this work, we formalize this problem and provide an initial solution. Given a collection of candidate mediators, we propose (a) a two-step method for predicting the causal responses of crude interventions; and (b) a testing procedure to identify mediators of crude interventions. We demonstrate, on a range of simulated and real-world-inspired examples, that our approach allows us to efficiently estimate the effect of crude interventions with limited data from new treatment regimes.
APA
Gultchin, L., Watson, D., Kusner, M. & Silva, R.. (2021). Operationalizing Complex Causes: A Pragmatic View of Mediation. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:3875-3885 Available from https://proceedings.mlr.press/v139/gultchin21a.html.

Related Material