The Feldman-Hájek Dichotomy for Countable Gaussian Mixtures and their Asymptotic Separability in High Dimensions
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911368006860800 |
|---|---|
| author | Michelucci, Umberto |
| author_facet | Michelucci, Umberto |
| contents | This paper establishes the theoretical foundations for the asymptotic separability of Gaussian Mixture Models (GMMs) in high dimensions by extending the classical Feldman-Hájek theorem. We first prove that a countable mixture of Gaussian measures is a well-defined probability measure. Our primary result, the Gaussian Mixture Dichotomy Theorem, demonstrates that the mutual singularity of individual Gaussian components is a sufficient condition for the mutual singularity of the resulting mixtures. We provide a rigorous proof and further discuss the ``Mixed Case,'' where the presence of even a single equivalent pair of components leads to partial absolute continuity via the Lebesgue decomposition, thereby defining the theoretical limits of perfect classification in infinite-dimensional spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Feldman-Hájek Dichotomy for Countable Gaussian Mixtures and their Asymptotic Separability in High Dimensions Michelucci, Umberto Statistics Theory 28EXX, 68Q32 This paper establishes the theoretical foundations for the asymptotic separability of Gaussian Mixture Models (GMMs) in high dimensions by extending the classical Feldman-Hájek theorem. We first prove that a countable mixture of Gaussian measures is a well-defined probability measure. Our primary result, the Gaussian Mixture Dichotomy Theorem, demonstrates that the mutual singularity of individual Gaussian components is a sufficient condition for the mutual singularity of the resulting mixtures. We provide a rigorous proof and further discuss the ``Mixed Case,'' where the presence of even a single equivalent pair of components leads to partial absolute continuity via the Lebesgue decomposition, thereby defining the theoretical limits of perfect classification in infinite-dimensional spaces. |
| title | The Feldman-Hájek Dichotomy for Countable Gaussian Mixtures and their Asymptotic Separability in High Dimensions |
| topic | Statistics Theory 28EXX, 68Q32 |
| url | https://arxiv.org/abs/2601.03911 |