Empirical Evaluation of the Performance of CEVAE under Misspecification of the Latent Dimensionality

Bachelor thesis (2022)

Authors

P. Barták Electrical Engineering, Mathematics and Computer Science

Contributors

J.H. Krijthe Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
S.R. Bongers Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
Rafael Bidarra Computer Graphics and Visualisation - EEMCS (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2022 Patrik Barták
Computer science Machine learning Statistics Causal Inference Neural network Causal machine learning VAE Latent variable model Confounder Causal reasoning
More Info
expand_more

Published Date

23-06-2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Causal machine learning deals with the inference of causal relationships between variables in observational datasets.
For certain datasets, it is correct to assume a causal graph where information about unobserved confounders can only be obtained through noisy proxies, and CEVAE aims to address this case.
The number of dimensions of the latent space modelled by CEVAE must be specified ahead of time, and this paper investigates the effect of this dimensionality misspecification on the performance of CEVAE.
Results support the idea that underspecification and overspecification both degrade the performance of CEVAE, but indicate that underspecification is worse, at least for the case with few confounders.
In general, the model does not always achieve best performance when the model dimensionality corresponds to the data dimensionality.
Finally, conclusions made on data with linear-Gaussian proxies are the same as those obtained with nonlinear-Gaussian proxies, which indicates these conclusions generalize over different datasets to some extent.