Learning soft interventions in complex equilibrium systems

Michel Besserve, Bernhard Schölkopf
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:170-180, 2022.

Abstract

Complex systems often contain feedback loops that can be described as cyclic causal models. Intervening in such systems may lead to counterintuitive effects, which cannot be inferred directly from the graph structure. After establishing a framework for differentiable soft interventions based on Lie groups, we take advantage of modern automatic differentiation techniques and their application to implicit functions in order to optimize interventions in cyclic causal models. We illustrate the use of this framework by investigating scenarios of transition to sustainable economies.

Cite this Paper

BibTeX
@InProceedings{pmlr-v180-besserve22a, title = {Learning soft interventions in complex equilibrium systems}, author = {Besserve, Michel and Sch{\"o}lkopf, Bernhard}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {170--180}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/besserve22a/besserve22a.pdf}, url = {https://proceedings.mlr.press/v180/besserve22a.html}, abstract = {Complex systems often contain feedback loops that can be described as cyclic causal models. Intervening in such systems may lead to counterintuitive effects, which cannot be inferred directly from the graph structure. After establishing a framework for differentiable soft interventions based on Lie groups, we take advantage of modern automatic differentiation techniques and their application to implicit functions in order to optimize interventions in cyclic causal models. We illustrate the use of this framework by investigating scenarios of transition to sustainable economies.} }
Endnote
%0 Conference Paper %T Learning soft interventions in complex equilibrium systems %A Michel Besserve %A Bernhard Schölkopf %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-besserve22a %I PMLR %P 170--180 %U https://proceedings.mlr.press/v180/besserve22a.html %V 180 %X Complex systems often contain feedback loops that can be described as cyclic causal models. Intervening in such systems may lead to counterintuitive effects, which cannot be inferred directly from the graph structure. After establishing a framework for differentiable soft interventions based on Lie groups, we take advantage of modern automatic differentiation techniques and their application to implicit functions in order to optimize interventions in cyclic causal models. We illustrate the use of this framework by investigating scenarios of transition to sustainable economies.
APA
Besserve, M. & Schölkopf, B.. (2022). Learning soft interventions in complex equilibrium systems. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:170-180 Available from https://proceedings.mlr.press/v180/besserve22a.html.

Related Material