In the univariate case, we show that by comparing the individual complexities
of univariate cause and effect, one can identify the cause and the effect,
without considering their interaction at all. In our framework, complexities
are captured by the reconstruction error of an autoencoder that operates on the
quantiles of the distribution. Comparing the reconstruction errors of the two
autoencoders, one for each variable, is shown to perform surprisingly well on
the accepted causality directionality benchmarks. Hence, the decision as to
which of the two is the cause and which is the effect may not be based on
causality but on complexity.
In the multivariate case, where one can ensure that the complexities of the
cause and effect are balanced, we propose a new adversarial training method
that mimics the disentangled structure of the causal model. We prove that in
the multidimensional case, such modeling is likely to fit the data only in the
direction of causality. Furthermore, a uniqueness result shows that the learned
model is able to identify the underlying causal and residual (noise)
components. Our multidimensional method outperforms the literature methods on
both synthetic and real world datasets.
Description
[2002.10007] A Critical View of the Structural Causal Model
%0 Journal Article
%1 galanti2020critical
%A Galanti, Tomer
%A Nabati, Ofir
%A Wolf, Lior
%D 2020
%K causal-analysis
%T A Critical View of the Structural Causal Model
%U http://arxiv.org/abs/2002.10007
%X In the univariate case, we show that by comparing the individual complexities
of univariate cause and effect, one can identify the cause and the effect,
without considering their interaction at all. In our framework, complexities
are captured by the reconstruction error of an autoencoder that operates on the
quantiles of the distribution. Comparing the reconstruction errors of the two
autoencoders, one for each variable, is shown to perform surprisingly well on
the accepted causality directionality benchmarks. Hence, the decision as to
which of the two is the cause and which is the effect may not be based on
causality but on complexity.
In the multivariate case, where one can ensure that the complexities of the
cause and effect are balanced, we propose a new adversarial training method
that mimics the disentangled structure of the causal model. We prove that in
the multidimensional case, such modeling is likely to fit the data only in the
direction of causality. Furthermore, a uniqueness result shows that the learned
model is able to identify the underlying causal and residual (noise)
components. Our multidimensional method outperforms the literature methods on
both synthetic and real world datasets.
@article{galanti2020critical,
abstract = {In the univariate case, we show that by comparing the individual complexities
of univariate cause and effect, one can identify the cause and the effect,
without considering their interaction at all. In our framework, complexities
are captured by the reconstruction error of an autoencoder that operates on the
quantiles of the distribution. Comparing the reconstruction errors of the two
autoencoders, one for each variable, is shown to perform surprisingly well on
the accepted causality directionality benchmarks. Hence, the decision as to
which of the two is the cause and which is the effect may not be based on
causality but on complexity.
In the multivariate case, where one can ensure that the complexities of the
cause and effect are balanced, we propose a new adversarial training method
that mimics the disentangled structure of the causal model. We prove that in
the multidimensional case, such modeling is likely to fit the data only in the
direction of causality. Furthermore, a uniqueness result shows that the learned
model is able to identify the underlying causal and residual (noise)
components. Our multidimensional method outperforms the literature methods on
both synthetic and real world datasets.},
added-at = {2020-03-04T13:40:45.000+0100},
author = {Galanti, Tomer and Nabati, Ofir and Wolf, Lior},
biburl = {https://www.bibsonomy.org/bibtex/22f8898a59526551d11558d19dc911852/kirk86},
description = {[2002.10007] A Critical View of the Structural Causal Model},
interhash = {bd3e746a1cc4ed48d249c501066bbe6a},
intrahash = {2f8898a59526551d11558d19dc911852},
keywords = {causal-analysis},
note = {cite arxiv:2002.10007},
timestamp = {2020-03-04T13:40:45.000+0100},
title = {A Critical View of the Structural Causal Model},
url = {http://arxiv.org/abs/2002.10007},
year = 2020
}