Metraipolis › archive › dc_3ff382b5665b
Self-regularization and structural adaptation of NPMLE for Gaussian mixture models in all dimensions — arXiv:2610.40566
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40566
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:30:59.979Z
- SHA-256 of the archived text
6d3252fb7c6c5c333cdae7a481e1704616ffa5a200733b8f808c346678136a73- Stable URL of this page
https://metraipolis.com/documento/dc_3ff382b5665b
How to cite
Self-regularization and structural adaptation of NPMLE for Gaussian mixture models in all dimensions — arXiv:2610.40566 — arXiv (en), https://arxiv.org/abs/2610.40566 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ff382b5665b (Metraipolis archive dc_3ff382b5665b, sha256 6d3252fb7c6c5c333cdae7a481e1704616ffa5a200733b8f808c346678136a73)
BibTeX
@misc{dc3ff382b5665b,
title = {Self-regularization and structural adaptation of NPMLE for Gaussian mixture models in all dimensions — arXiv:2610.40566},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40566},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ff382b5665b; sha256 6d3252fb7c6c5c333cdae7a481e1704616ffa5a200733b8f808c346678136a73},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40566. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We establish structural properties of the nonparametric maximum likelihood estimator (NPMLE) for $d$-dimensional Gaussian mixtures whose means lie in a hypercube. We show that, with high probability, the NPMLE based on $n$ independent observations self-regularizes by fitting a mixture model with $O((\frac{\log n}{\log\log n})^d)$ components, achieving the optimal model complexity without explicit model selection. Furthermore, the NPMLE exhibits a structural adaptation property: For data drawn from a finite mixture, the number of fitted components is bounded in probability as $n\to\infty$. Our proof applies a multivariate Jensen-type bound to control the typical number of critical points of the KKT function associated with the first-order optimality conditions. The key step is to lower bound its gradient norm uniformly on complex spheres. We establish this lower bound by decomposing the KKT function into an empirical fluctuation term and a relative density estimation error term, combining small-ball probability estimates for the former with polynomial approximation and Hellinger error bounds for the latter.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.40566 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:13:28.614Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).