Statistical guarantees for the EM algorithm: from population to sample-based analysis
From MaRDI portal
Publication:524451
DOI10.1214/16-AOS1435zbMath1367.62052arXiv1408.2156OpenAlexW2962737134MaRDI QIDQ524451
Sivaraman Balakrishnan, Martin J. Wainwright, Bin Yu
Publication date: 2 May 2017
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1408.2156
Related Items (66)
Supermix: sparse regularization for mixtures ⋮ GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models ⋮ Sketched learning for image denoising ⋮ Network inference from temporally dependent grouped observations ⋮ A new class of stochastic EM algorithms. Escaping local maxima and handling intractable sampling ⋮ Analysis of a generalised expectation–maximisation algorithm for Gaussian mixture models: a control systems perspective ⋮ Iterative algorithm for discrete structure recovery ⋮ Subgroup-effects models for the analysis of personal treatment effects ⋮ Solution manifold and its statistical applications ⋮ Estimating finite mixtures of ordinal graphical models ⋮ Universal inference ⋮ The computational asymptotics of Gaussian variational inference and the Laplace approximation ⋮ Parameter recovery in two-component contamination mixtures: the \(L^2\) strategy ⋮ A general frame for uncertainty propagation under multimodally distributed random variables ⋮ Uniform consistency in nonparametric mixture models ⋮ Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ Likelihood Maximization and Moment Matching in Low <scp>SNR</scp> Gaussian Mixture Models ⋮ An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization ⋮ Oscillating neural circuits: Phase, amplitude, and the complex normal distribution ⋮ Statistical Inference with Local Optima ⋮ Statistical analysis of Markov switching vector autoregression models with endogenous explanatory variables ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Geometry of EM and related iterative algorithms ⋮ Moment Estimation for Nonparametric Mixture Models through Implicit Tensor Decomposition ⋮ On the nonparametric maximum likelihood estimator for Gaussian location mixture densities with application to Gaussian denoising ⋮ Deep parameterizations of pairwise and triplet Markov models for unsupervised classification of sequential data ⋮ Optimal estimation and computational limit of low-rank Gaussian mixtures ⋮ A tensor-EM method for large-scale latent class analysis with binary responses ⋮ Improving the accuracy and internal consistency of regression-based clustering of high-dimensional datasets ⋮ Likelihood-based analysis in mixture global vars ⋮ Estimating a network from multiple noisy realizations ⋮ Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems ⋮ A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering ⋮ Optimal estimation of Gaussian mixtures via denoised method of moments ⋮ Robust high dimensional expectation maximization algorithm via trimmed hard thresholding ⋮ Improved convergence guarantees for learning Gaussian mixture models by EM and gradient EM ⋮ Homomorphic sensing of subspace arrangements ⋮ Simultaneous Clustering and Estimation of Heterogeneous Graphical Models ⋮ Singularity, misspecification and the convergence rate of EM ⋮ Rate optimal estimation and confidence intervals for high-dimensional regression with missing covariates ⋮ Statistical Inference for High-Dimensional Vector Autoregression with Measurement Error ⋮ Sequential estimation for mixture of regression models for heterogeneous population ⋮ A new algorithm for inference in HMM's with lower span complexity ⋮ Loss modeling with the size-biased lognormal mixture and the entropy regularized EM algorithm ⋮ A diffusion process perspective on posterior contraction rates for parameters ⋮ Tuning-free sparse clustering via alternating hard-thresholding ⋮ Mixture conditional regression with ultrahigh dimensional text data for estimating extralegal factor effects ⋮ Statistical convergence of the EM algorithm on Gaussian mixture models ⋮ Fundamental limits of low-rank matrix estimation with diverging aspect ratios ⋮ Nonparametric Finite Mixture of Gaussian Graphical Models ⋮ Reliable clustering of Bernoulli mixture models ⋮ Semiparametric mixture regression with unspecified error distributions ⋮ Community detection with dependent connectivity ⋮ Finding Low-Rank Solutions via Nonconvex Matrix Factorization, Efficiently and Provably ⋮ Statistical and Computational Guarantees for the Baum-Welch Algorithm ⋮ A flexible probabilistic framework for large-margin mixture of experts ⋮ Large-sample properties of unsupervised estimation of the linear discriminant using projection pursuit ⋮ Exponential-Family Embedding With Application to Cell Developmental Trajectories for Single-Cell RNA-Seq Data ⋮ Covariate Regularized Community Detection in Sparse Graphs ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Hidden Integrality and Semirandom Robustness of SDP Relaxation for Sub-Gaussian Mixture Model ⋮ From inexact optimization to learning via gradient concentration ⋮ Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in \(O(\sqrt{n})\) iterations ⋮ On the curved exponential family in the Stochastic Approximation Expectation Maximization Algorithm
This page was built for publication: Statistical guarantees for the EM algorithm: from population to sample-based analysis
