# Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choice

arXiv: https://arxiv.org/abs/2310.18212 · HTML: https://mlsanity.com/paper/2310.18212/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Builds on (most cited first, 18 of 18)

- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Gradient-Based Neural DAG Learning](https://mlsanity.com/paper/1906.02226/) (2019)
- [Learning Sparse Nonparametric DAGs](https://mlsanity.com/paper/1909.13189/) (2019)
- [CAM: Causal additive models, high-dimensional order search and penalized regression](https://mlsanity.com/paper/1310.1533/) (2013)
- [Hyper-Parameter Optimization: A Review of Algorithms and Applications](https://mlsanity.com/paper/2003.05689/) (2020)
- [Hyperparameter Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2007.09055/) (2020)
- [Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark](https://mlsanity.com/paper/2309.00367/) (2023)
- [gCastle: A Python Toolbox for Causal Discovery](https://mlsanity.com/paper/2111.15155/) (2021)
- [On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning](https://mlsanity.com/paper/2102.13651/) (2021)
- [Unsuitability of NOTEARS for Causal Graph Discovery](https://mlsanity.com/paper/2104.05441/) (2021)
- [Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation](https://mlsanity.com/paper/1906.01732/) (2019)
- [In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2302.02923/) (2023)
- [Benchpress: A Scalable and Versatile Workflow for Benchmarking Structure Learning Algorithms](https://mlsanity.com/paper/2107.03863/) (2021)
- [Quantitative probing: Validating causal models using quantitative domain knowledge](https://mlsanity.com/paper/2209.03013/) (2022)
- [The Challenges of Hyperparameter Tuning for Accurate Causal Effect Estimation](https://mlsanity.com/paper/2303.01412/) (2023)
- [Marginalization and Conditioning for LWF Chain Graphs](https://mlsanity.com/paper/1405.7129/) (2014)
- [Automated Hyperparameter Selection for the PC Algorithm](https://mlsanity.com/paper/2011.01889/) (2020)
- [Tuning structure learning algorithms with out-of-sample and resampling strategies](https://mlsanity.com/paper/2306.13932/) (2023)

## Built on by (most cited first, 4 of 4)

- [Separation-based distance measures for causal graphs](https://mlsanity.com/paper/2402.04952/) (2024)
- [Double Machine Learning for Static Panel Models with Fixed Effects](https://mlsanity.com/paper/2312.08174/) (2023)
- [Rethinking Chronological Causal Discovery with Signal Processing](https://mlsanity.com/paper/2602.19903/) (2026)
- [xtdml: Double Machine Learning Estimation to Static Panel Data Models with Fixed Effects in R](https://mlsanity.com/paper/2512.15965/) (2025)

## Abstract (arXiv)

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.