The Causal Information Bottleneck and Optimal Causal Variable Abstractions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918054030475264 |
|---|---|
| author | Simoes, Francisco N. F. Q. Dastani, Mehdi van Ommen, Thijs |
| author_facet | Simoes, Francisco N. F. Q. Dastani, Mehdi van Ommen, Thijs |
| contents | To effectively study complex causal systems, it is often useful to construct abstractions of parts of the system by discarding irrelevant details while preserving key features. The Information Bottleneck (IB) method is a widely used approach to construct variable abstractions by compressing random variables while retaining predictive power over a target variable. Traditional methods like IB are purely statistical and ignore underlying causal structures, making them ill-suited for causal tasks. We propose the Causal Information Bottleneck (CIB), a causal extension of the IB, which compresses a set of chosen variables while maintaining causal control over a target variable. This method produces abstractions of (sets of) variables which are causally interpretable, give us insight about the interactions between the abstracted variables and the target variable, and can be used when reasoning about interventions. We present experimental results demonstrating that the learned abstractions accurately capture causal relations as intended. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Causal Information Bottleneck and Optimal Causal Variable Abstractions Simoes, Francisco N. F. Q. Dastani, Mehdi van Ommen, Thijs Machine Learning Artificial Intelligence Information Theory To effectively study complex causal systems, it is often useful to construct abstractions of parts of the system by discarding irrelevant details while preserving key features. The Information Bottleneck (IB) method is a widely used approach to construct variable abstractions by compressing random variables while retaining predictive power over a target variable. Traditional methods like IB are purely statistical and ignore underlying causal structures, making them ill-suited for causal tasks. We propose the Causal Information Bottleneck (CIB), a causal extension of the IB, which compresses a set of chosen variables while maintaining causal control over a target variable. This method produces abstractions of (sets of) variables which are causally interpretable, give us insight about the interactions between the abstracted variables and the target variable, and can be used when reasoning about interventions. We present experimental results demonstrating that the learned abstractions accurately capture causal relations as intended. |
| title | The Causal Information Bottleneck and Optimal Causal Variable Abstractions |
| topic | Machine Learning Artificial Intelligence Information Theory |
| url | https://arxiv.org/abs/2410.00535 |