Linear causal disentanglement via higher-order cumulants
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929410586705920 |
|---|---|
| author | Carreno, Paula Leyes Meroni, Chiara Seigal, Anna |
| author_facet | Carreno, Paula Leyes Meroni, Chiara Seigal, Anna |
| contents | Linear causal disentanglement is a recent method in causal representation learning to describe a collection of observed variables via latent variables with causal dependencies between them. It can be viewed as a generalization of both independent component analysis and linear structural equation models. We study the identifiability of linear causal disentanglement, assuming access to data under multiple contexts, each given by an intervention on a latent variable. We show that one perfect intervention on each latent variable is sufficient and in the worst case necessary to recover parameters under perfect interventions, generalizing previous work to allow more latent than observed variables. We give a constructive proof that computes parameters via a coupled tensor decomposition. For soft interventions, we find the equivalence class of latent graphs and parameters that are consistent with observed data, via the study of a system of polynomial equations. Our results hold assuming the existence of non-zero higher-order cumulants, which implies non-Gaussianity of variables. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04605 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Linear causal disentanglement via higher-order cumulants Carreno, Paula Leyes Meroni, Chiara Seigal, Anna Machine Learning Algebraic Geometry Combinatorics Statistics Theory 13P15, 15A69, 62H22, 62R01, 68Q32 Linear causal disentanglement is a recent method in causal representation learning to describe a collection of observed variables via latent variables with causal dependencies between them. It can be viewed as a generalization of both independent component analysis and linear structural equation models. We study the identifiability of linear causal disentanglement, assuming access to data under multiple contexts, each given by an intervention on a latent variable. We show that one perfect intervention on each latent variable is sufficient and in the worst case necessary to recover parameters under perfect interventions, generalizing previous work to allow more latent than observed variables. We give a constructive proof that computes parameters via a coupled tensor decomposition. For soft interventions, we find the equivalence class of latent graphs and parameters that are consistent with observed data, via the study of a system of polynomial equations. Our results hold assuming the existence of non-zero higher-order cumulants, which implies non-Gaussianity of variables. |
| title | Linear causal disentanglement via higher-order cumulants |
| topic | Machine Learning Algebraic Geometry Combinatorics Statistics Theory 13P15, 15A69, 62H22, 62R01, 68Q32 |
| url | https://arxiv.org/abs/2407.04605 |