Robustness of algorithms for causal structure learning to hyperparameter choice

Publication type

Journal Article

Authors

Publication date

June 1, 2024

Summary:

Hyperparameters play a critical role in machine learning. Hyperparameter tuning can make the difference between state-of-the-art and poor prediction performance for any algorithm, but it is particularly challenging for structure learning due to its unsupervised nature. As a result, hyperparameter tuning is often neglected in favour of using the default values provided by a particular implementation of an algorithm. While there have been numerous studies on performance evaluation of causal discovery algorithms, how hyperparameters affect individual algorithms, as well as the choice of the best algorithm for a specific problem, has not been studied in depth before. This work addresses this gap by investigating the influence of hyperparameters on causal structure learning tasks. Specifically, we perform an empirical evaluation of hyperparameter selection for some seminal learning algorithms on datasets of varying levels of complexity. We find that, while the choice of algorithm remains crucial to obtaining state-of-the-art performance, hyperparameter selection in ensemble settings strongly influences the choice of algorithm, in that a poor choice of hyperparameters can lead to analysts using algorithms which do not give state-of-the-art performance for their data.

Published in

Proceedings of the Third Conference on Causal Learning and Reasoning: Proceedings of Machine Learning Research

Volume and page numbers

Volume: 236 , p.703 -739

ISSN

26403498

Subjects

Link

https://proceedings.mlr.press/v236/machlanski24a.html

#578202

News

Latest findings, new research

Publications search

Search all research by subject and author

Podcasts

Researchers discuss their findings and what they mean for society

Projects

Background and context, methods and data, aims and outputs

Events

Conferences, seminars and workshops

Survey methodology

Specialist research, practice and study

Taking the long view

ISER's annual report

Themes

Key research themes and areas of interest