ArXiv Preprint
Hypothesis testing and the usage of expert knowledge, or causal priors, has
not been well explored in the context of generative models. We propose a novel
set of generative architectures, Causal Gen and Causal Variational Gen, that
can utilize nonparametric structural causal knowledge combined with a deep
learning functional approximation. We show how, using a deliberate (non-random)
split of training and testing data, these models can generalize better to
similar, but out-of-distribution data points, than non-causal generative models
and prediction models such as Variational autoencoders and Fully Connected
Neural Networks. We explore using this generalization error as a proxy for
causal model hypothesis testing. We further show how dropout can be used to
learn functional relationships of structural models that are difficult to learn
with traditional methods. We validate our methods on a synthetic pendulum
dataset, as well as a trauma surgery ground level fall dataset.
Jeffrey Jiang, Omead Pooladzandi, Sunay Bhat, Gregory Pottie
2022-10-20
