# Markov Blanket Discovery using Minimum Message Length

arXiv: https://arxiv.org/abs/2107.08140 · HTML: https://mlsanity.com/paper/2107.08140/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 39 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 3 of 3)

- [Learning Equivalence Classes of Bayesian Networks Structures](https://mlsanity.com/paper/1302.3566/) (2013)
- [Markov Boundary Discovery with Ridge Regularized Linear Models](https://mlsanity.com/paper/1509.03935/) (2015)
- [Learning Bayesian Networks with Restricted Causal Interactions](https://mlsanity.com/paper/1301.6727/) (2013)

## Built on by (most cited first, 1 of 1)

- [CaberNet: Causal Representation Learning for Cross-Domain HVAC Energy Prediction](https://mlsanity.com/paper/2511.06634/) (2025)

## Abstract (arXiv)

Causal discovery automates the learning of causal Bayesian networks from data and has been of active interest from their beginning. With the sourcing of large data sets off the internet, interest in scaling up to very large data sets has grown. One approach to this is to parallelize search using Markov Blanket (MB) discovery as a first step, followed by a process of combining MBs in a global causal model. We develop and explore three new methods of MB discovery using Minimum Message Length (MML) and compare them empirically to the best existing methods, whether developed specifically as MB discovery or as feature selection. Our best MML method is consistently competitive and has some advantageous features.