Singular Learning Theory for Factor Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912718977499136 |
|---|---|
| author | Drton, Mathias Gross, Elizabeth Kosta, Dimitra Leykin, Anton Sullivant, Seth Windisch, Daniel |
| author_facet | Drton, Mathias Gross, Elizabeth Kosta, Dimitra Leykin, Anton Sullivant, Seth Windisch, Daniel |
| contents | Watanabe's singular learning theory provides a framework for asymptotic analysis of Bayesian model selection for statistical models with singularities, where traditional statistical regularity assumptions fail. Learning coefficients, also known as real log canonical thresholds, play a central role in singular learning, as they govern the asymptotic behavior of Bayesian marginal likelihood integrals in settings where the Laplace approximations used for regular statistical models are not applicable. Learning coefficients are algebraic invariants that quantify the geometric complexity of a model and reveal how the singular structure impacts the model's generalization properties. In this paper, we apply algebraic methods to study the learning coefficients of factor analysis models, which are widely used latent variable models for continuously distributed data. Our main results provide a general upper bound for the learning coefficients as well as exact formulas for specific cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15419 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Singular Learning Theory for Factor Analysis Drton, Mathias Gross, Elizabeth Kosta, Dimitra Leykin, Anton Sullivant, Seth Windisch, Daniel Statistics Theory Algebraic Geometry 62H25, 62F15, 62R01, 14E15, 14P05 Watanabe's singular learning theory provides a framework for asymptotic analysis of Bayesian model selection for statistical models with singularities, where traditional statistical regularity assumptions fail. Learning coefficients, also known as real log canonical thresholds, play a central role in singular learning, as they govern the asymptotic behavior of Bayesian marginal likelihood integrals in settings where the Laplace approximations used for regular statistical models are not applicable. Learning coefficients are algebraic invariants that quantify the geometric complexity of a model and reveal how the singular structure impacts the model's generalization properties. In this paper, we apply algebraic methods to study the learning coefficients of factor analysis models, which are widely used latent variable models for continuously distributed data. Our main results provide a general upper bound for the learning coefficients as well as exact formulas for specific cases. |
| title | Singular Learning Theory for Factor Analysis |
| topic | Statistics Theory Algebraic Geometry 62H25, 62F15, 62R01, 14E15, 14P05 |
| url | https://arxiv.org/abs/2511.15419 |