Convergence rates of latent topic models under relaxed identifiability conditions

DOI10.1214/18-EJS1516zbMath1433.62092arXiv1710.11070OpenAlexW2964350306WikidataQ128626613 ScholiaQ128626613MaRDI QIDQ1711601

Yining Wang

Publication date: 18 January 2019

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1710.11070

zbMATH Keywords

rates of convergencemaximum likelihoodtopic modelslatent Dirichlet allocation

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Learning Topic Models: Identifiability and Finite-Sample Analysis

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Global identifiability of linear structural equation models
• Borrowing strengh in hierarchical Bayes: posterior concentration of the Dirichlet base measure
• Sharper bounds for Gaussian and empirical processes
• Optimal rate of convergence for finite mixture models
• Convergence of latent mixing measures in finite and infinite mixture models
• Posterior contraction of the population polytope in finite admixture models
• A spectral algorithm for latent Dirichlet allocation
• Tensor decompositions for learning latent variable models
• Learning Mixtures of Gaussians in High Dimensions
• Learning mixtures of spherical gaussians
• Condition Estimates
• Algebraic Geometry and Statistical Learning Theory
• Asymptotic Statistics
• Algebraic Problems in Structural Equation Modeling
• 10.1162/jmlr.2003.3.4-5.993
• Singularity Structures and Impacts on Parameter Estimation in Finite Mixtures of Distributions
• Identifiability of directed Gaussian graphical models with one latent source

This page was built for publication: Convergence rates of latent topic models under relaxed identifiability conditions