Algorithmic causal structure emerging through compression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915207364739072 |
|---|---|
| author | Wendong, Liang Buchholz, Simon Schölkopf, Bernhard |
| author_facet | Wendong, Liang Buchholz, Simon Schölkopf, Bernhard |
| contents | We explore the relationship between causality, symmetry, and compression. We build on and generalize the known connection between learning and compression to a setting where causal models are not identifiable. We propose a framework where causality emerges as a consequence of compressing data across multiple environments. We define algorithmic causality as an alternative definition of causality when traditional assumptions for causal identifiability do not hold. We demonstrate how algorithmic causal and symmetric structures can emerge from minimizing upper bounds on Kolmogorov complexity, without knowledge of intervention targets. We hypothesize that these insights may also provide a novel perspective on the emergence of causality in machine learning models, such as large language models, where causal relationships may not be explicitly identifiable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04210 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Algorithmic causal structure emerging through compression Wendong, Liang Buchholz, Simon Schölkopf, Bernhard Machine Learning Artificial Intelligence Computational Complexity Information Theory We explore the relationship between causality, symmetry, and compression. We build on and generalize the known connection between learning and compression to a setting where causal models are not identifiable. We propose a framework where causality emerges as a consequence of compressing data across multiple environments. We define algorithmic causality as an alternative definition of causality when traditional assumptions for causal identifiability do not hold. We demonstrate how algorithmic causal and symmetric structures can emerge from minimizing upper bounds on Kolmogorov complexity, without knowledge of intervention targets. We hypothesize that these insights may also provide a novel perspective on the emergence of causality in machine learning models, such as large language models, where causal relationships may not be explicitly identifiable. |
| title | Algorithmic causal structure emerging through compression |
| topic | Machine Learning Artificial Intelligence Computational Complexity Information Theory |
| url | https://arxiv.org/abs/2502.04210 |