Optimal estimation of Gaussian mixtures via denoised method of moments

DOI10.1214/19-AOS1873zbMath1455.62075arXiv1807.07237MaRDI QIDQ2215721

Yihong Wu, Pengkun Yang

Publication date: 14 December 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.07237

zbMATH Keywords

semidefinite programmingGaussian mixtureGauss quadraturedeconvolutionfinite mixture modelmethod of momentsWasserstein distanceminimax optimalitymoment space

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonparametric estimation (62G05) Minimax procedures in statistical decision theory (62C20)

Related Items (16)

GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models ⋮ Learning diagonal Gaussian mixture models and incomplete tensor decompositions ⋮ Minimax bounds for estimating multivariate Gaussian location mixtures ⋮ The application of the distributed-order time fractional Bloch model to magnetic resonance imaging ⋮ Uniform consistency in nonparametric mixture models ⋮ Optimal estimation of high-dimensional Gaussian location mixtures ⋮ Fisher-Pitman Permutation Tests Based on Nonparametric Poisson Mixtures with Application to Single Cell Genomics ⋮ Optimal estimation and computational limit of low-rank Gaussian mixtures ⋮ Optimal Bayesian estimation of Gaussian mixtures with growing number of components ⋮ Unnamed Item ⋮ Estimating the number of components in finite mixture models via the group-sort-fuse procedure ⋮ Convergence of de Finetti's mixing measure in latent structure models for observed exchangeable sequences ⋮ Learning mixtures of permutations: groups of pairwise comparisons and combinatorial method of moments ⋮ Uncertainty Quantification of Bifurcations in Random Ordinary Differential Equations ⋮ Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in \(O(\sqrt{n})\) iterations ⋮ Asymptotics of smoothed Wasserstein distances

Uses Software

• OPQ
• CVXPY

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Large Sample Properties of Generalized Method of Moments Estimators
• Minimax bounds for estimation of normal mixtures
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Choosing initial values for the EM algorithm for finite mixtures
• Estimation of the mixing distribution for a normal mean with applications to the compound decision problem
• Moment matrices: Applications in mixtures
• Spectrum estimation from samples
• Rates of convergence for the Gaussian mixture sieve.
• Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities.
• Optimal rate of convergence for finite mixture models
• Convergence of latent mixing measures in finite and infinite mixture models
• Strong identifiability and optimal minimax rates for finite mixture estimation
• Introduction to empirical processes and semiparametric inference
• Finite mixture and Markov switching models.
• Alternative EM methods for nonparametric finite mixture models
• CVXPY: A Python-Embedded Modeling Language for Convex Optimization
• Efficiently learning mixtures of two Gaussians
• Tensor decompositions for learning latent variable models
• Tight Bounds for Learning a Mixture of Two Gaussians
• Consistency of the Maximum Likelihood Estimator in the Presence of Infinitely Many Incidental Parameters
• Mixture Densities, Maximum Likelihood and the EM Algorithm
• Nonparametric Maximum Likelihood Estimation of a Mixing Distribution
• Asymptotic Statistics
• Convex Optimization, Shape Constraints, Compound Decisions, and Empirical Bayes Rules
• Mixture models, robustness, and sum of squares proofs
• Estimation of analytic functions
• Polynomial Learning of Distribution Families
• Construction of Sequences Estimating the Mixing Distribution
• Calculation of Gauss Quadrature Rules
• Geometry of moment spaces
• A cautionary note on likelihood ratio tests in mixture models

This page was built for publication: Optimal estimation of Gaussian mixtures via denoised method of moments