On the Geometry of Separation in Finite Gaussian Mixtures

• URL: http://arxiv.org/abs/2606.16179v1
• Date: Mon, 15 Jun 2026 03:49:33 GMT
• Title: On the Geometry of Separation in Finite Gaussian Mixtures
• Abstract summary: We study the effects of the minimum component separation on the convergence rates of parameter estimation in finite Gaussian mixtures.<n>We develop a unified geometric framework based on novel Hellinger lower bounds.<n>We obtain separation-dependent convergence rates that continuously interpolate between point-wise and uniform estimation regimes.
• Score: 93.28335398145147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study an open problem of understanding the effects of the minimum component separation on the convergence rates of parameter estimation in finite Gaussian mixtures. We address this by developing a unified geometric framework based on novel Hellinger lower bounds that directly relate discrepancies between mixture densities directly to Wasserstein distances between their underlying mixing measures, with explicit dependence on both the minimum separation and the minimum weight. Our approach combines carefully designed interpolation polynomials with confluent divided difference techniques to construct specialized moment-extraction test functions. When the number of components is known, these bounds uncover a localization phenomenon: the separation complexity is driven strictly by the spatial configuration of mixture components, namely, whether they are concentrated in a single cluster, partitioned into multiple clusters separated by a macroscopic gap, or arranged without any structural constraints. On the other hand, when the number of components becomes unknown and is over-specified, the separation complexity is slightly reduced, while the minimum mixture weight disappears entirely from the convergence rates due to a transition from first-order to second-order Wasserstein geometry. As a consequence, we obtain separation-dependent convergence rates that continuously interpolate between point-wise and uniform estimation regimes, thereby settling the fundamental limits of parameter recovery in finite Gaussian mixtures.

Related papers

• Characterizing Heterogeneous Rates in Finite Mixture Estimation via Partial Optimal Transport [88.55403215843967]
  Voronoi-based partial optimal transport (VPOT) for obtaining refined local and global convergence guarantees for the maximum likelihood estimator of the mixing measure.<n>Results hold in arbitrary fixed dimension without requiring mixing proportions to be uniformly bounded away from zero or prior knowledge of the true number of mixture components.
  arXiv  Detail & Related papers  (2026-09-15T04:32:53Z)
• Mixtures Closest to a Given Measure: A Semidefinite Programming Approach [1.7969777786551424]
  We study the problem of approximating a target measure, available only through finitely many of its moments.<n>Unlike many existing approaches, the parameter set is not assumed to be finite.<n>We present an application to clustering, where our framework serves as a stand-alone method or as a preprocessing step.
  arXiv  Detail & Related papers  (2025-09-26T19:51:21Z)
• On the best approximation by finite Gaussian mixtures [7.084611118322622]
  We consider the problem of approximating a general Gaussian location mixture by finite mixtures.<n>The minimum order of finite mixtures that achieve a prescribed accuracy is determined within constant factors.
  arXiv  Detail & Related papers  (2024-04-13T06:57:44Z)
• Targeted Separation and Convergence with Kernel Discrepancies [61.973643031360254]
  kernel-based discrepancy measures are required to (i) separate a target P from other probability measures or (ii) control weak convergence to P.<n>In this article we derive new sufficient and necessary conditions to ensure (i) and (ii)<n>For MMDs on separable metric spaces, we characterize those kernels that separate Bochner embeddable measures and introduce simple conditions for separating all measures with unbounded kernels.
  arXiv  Detail & Related papers  (2022-09-26T16:41:16Z)
• Quantum Coherent States of Interacting Bose-Fermi Mixtures in One Dimension [68.8204255655161]
  We study two-component atomic gas mixtures in one dimension involving both bosons and fermions. We report a rich variety of coherent ground-state phases that vary with the intrinsic and relative strength of the interactions.
  arXiv  Detail & Related papers  (2021-10-26T17:52:37Z)
• Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians [45.392805695921666]
  We exploit a connection between total variation distance and the characteristic function of the mixture. We derive new lower bounds on the total variation distance between pairs of two-component Gaussian mixtures.
  arXiv  Detail & Related papers  (2021-09-02T16:32:16Z)
• Applying splitting methods with complex coefficients to the numerical integration of unitary problems [0.0]
  We prove that a particular class of conjugates are conjugate to unitary methods for sufficiently small step sizes when applied to problems defined in the group $mathrmSU(2)$. In the general case, the error in both the energy and the norm of the numerical approximation provided by these methods does not possess a secular component over long time intervals, when combined with pseudo-spectral discretization techniques in space.
  arXiv  Detail & Related papers  (2021-04-06T10:38:33Z)
• Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations [84.81435917024983]
  This work proposes an algorithm that consistently estimates any identifiable mixture model from grouped observations. A practical implementation is provided for paired observations, and the approach is shown to outperform existing methods.
  arXiv  Detail & Related papers  (2020-06-12T20:44:22Z)
• Uniform Convergence Rates for Maximum Likelihood Estimation under Two-Component Gaussian Mixture Models [13.769786711365104]
  We derive uniform convergence rates for the maximum likelihood estimator and minimax lower bounds for parameter estimation. We assume the mixing proportions of the mixture are known and fixed, but make no separation assumption on the underlying mixture components.
  arXiv  Detail & Related papers  (2020-06-01T04:13:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.