Weak Limits of Parameter Estimation in Strongly Identifiable Mixture Models

Abstract

We study the asymptotic behavior of global maximum likelihood estimation in finite mixtures with an unknown number of components bounded by k. Although convergence rates are well understood under strong identifiability, they do not determine the limiting distribution of mixing-measure loss. Under second-order strong identifiability, we establish two geometric results that connect density asymptotics to uncertainty about the mixing measure. First, we characterize the exact attainable density tangent set, accounting for the component budget shared by nonlocal vanishing components and local splitting directions. Second, we derive a sequential first-order expansion of squared Wasserstein loss, showing that its leading transportation cost is uniquely determined by the relative-density direction. Together with a Gaussian likelihood argmax theorem, these results yield joint weak convergence of the relative-density maximum likelihood estimator and √n W₂²(Ĝ_n,G_*). The density limit maximizes a Gaussian likelihood process over the attainable tangent set, and the induced limit of n^1/4W₂(Ĝ_n,G_*) is generally non-Gaussian. We establish consistency of an m-out-of-n parametric bootstrap when m→∞ and m/n→0. Numerical studies assess the approximation and distinguish bootstrap and optimization errors; a flow-cytometry application illustrates uncertainty summaries invariant to component labeling under a working mixture model.

Brown's loss function and estimation of the scale parameter and the entropy in scale mixture models with unknown location
Stavros Kourouklis
arXiv9 Oct 2026PreprintarXiv licenceFull textStatisticsarXiv
Fundamental Limits of Joint Target Detection and Parameter Estimation - Characterizing Mixed-State Sensing Limits via Posterior Entropy Volume
Dazhuan Xu, Nan Wang, Han Zhang
arXiv9 Sep 2026PreprintarXiv licenceFull textGeneral mathematicsarXiv
The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts
Aidar Amankulov, Denis Mamatin
arXiv1 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Existence of solutions for a large defocusing parameter in a strongly indefinite Schrödinger equation
Bartosz Bieganowski
arXiv20 Sep 2026PreprintCC BY 4.0Full textAnalysis & PDEsarXiv
Sandwich Variance Estimation in Scale Mixture of Skew-Normal Linear Mixed Models.
Keyliane Travassos, Larissa A Matos, Fernanda L Schumacher
Statistics in medicine1 Oct 2026Peer-reviewedCC BYFull textStatisticsEurope PMC

Cite

BibTeX RIS

BibTeX

@misc{le2026weak,
  title = {{Weak Limits of Parameter Estimation in Strongly Identifiable Mixture Models}},
  author = {Dung Le and Trang Pham and Alessandro Rinaldo and Nhat Ho},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.25857},
  eprint = {2610.25857},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.25857},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Weak Limits of Parameter Estimation in Strongly Identifiable Mixture Models
AU  - Dung Le
AU  - Trang Pham
AU  - Alessandro Rinaldo
AU  - Nhat Ho
PY  - 2026
DA  - 2026/10/19
PB  - arXiv
DO  - 10.48550/arxiv.2610.25857
UR  - https://arxiv.org/abs/2610.25857
AB  - We study the asymptotic behavior of global maximum likelihood estimation in finite mixtures with an unknown number of components bounded by k. Although convergence rates are well understood under strong identifiability, they do not determine the limiting distribution of mixing-measure loss. Under second-order strong identifiability, we establish two geometric results that connect density asymptotics to uncertainty about the mixing measure. First, we characterize the exact attainable density tangent set, accounting for the component budget shared by nonlocal vanishing components and local splitting directions. Second, we derive a sequential first-order expansion of squared Wasserstein loss, showing that its leading transportation cost is uniquely determined by the relative-density direction. Together with a Gaussian likelihood argmax theorem, these results yield joint weak convergence of the relative-density maximum likelihood estimator and √n W_2^2(Ĝ_n,G_*). The density limit maximizes a Gaussian likelihood process over the attainable tangent set, and the induced limit of n^1/4W_2(Ĝ_n,G_*) is generally non-Gaussian. We establish consistency of an m-out-of-n parametric bootstrap when m→∞ and m/n→0. Numerical studies assess the approximation and distinguish bootstrap and optimization errors; a flow-cytometry application illustrates uncertainty summaries invariant to component labeling under a working mixture model.
ER  -

Abstract

Related

Cite