Frequentist Consistency of Variational Bayes

DOI10.1080/01621459.2018.1473776zbMath1428.62119arXiv1705.03439OpenAlexW2612481336WikidataQ129739249 ScholiaQ129739249MaRDI QIDQ5242465

David M. Blei, Yixin Wang

Publication date: 12 November 2019

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1705.03439

zbMATH Keywords

consistencyasymptotic normalityvariational methodsBayesian inferencestatistical computingBernstein-von Mises

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Asymptotic distribution theory in statistics (62E20) Bayesian inference (62F15)

Related Items

Bayesian sparse convex clustering via global-local shrinkage priors, Variational Bayesian approximation of inverse problems using sparse precision matrices, The determination of biosimilarity margin and the assessment of biosimilarity for an (m+1)-arm parallel design, Gibbs sampler and coordinate ascent variational inference: A set-theoretical review, The computational asymptotics of Gaussian variational inference and the Laplace approximation, Bayesian Approaches to Shrinkage and Sparse Estimation, Fast and universal estimation of latent variable models using extended variational approximations, Comprehensive study of variational Bayes classification for dense deep neural networks, Statistical foundation of variational Bayes neural networks, BAYESIAN DYNAMIC VARIABLE SELECTION IN HIGH DIMENSIONS, Black Box Variational Bayesian Model Averaging, Deep Compositional Spatial Models, New metrics and tests for subject prevalence in documents based on topic modeling, Unnamed Item, An Approximated Collapsed Variational Bayes Approach to Variable Selection in Linear Regression, Variational Bayes in State Space Models: Inferential and Predictive Accuracy, Variational discriminant analysis with variable selection, A Zero-Inflated Logistic Normal Multinomial Model for Extracting Microbial Compositions, Concentration of tempered posteriors and of their variational approximations, Local convexity of the TAP free energy and AMP convergence for \(\mathbb{Z}_2\)-synchronization, Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency, Uncertainty quantification for sparse spectral variational approximations in Gaussian process regression, Variational Bayes for High-Dimensional Linear Regression With Sparse Priors, Convergence rates of variational posterior distributions, Theoretical and computational guarantees of mean field variational inference for community detection, Technical Note—Consistency Analysis of Sequential Learning Under Approximate Bayesian Inference, Non-stationary multi-layered Gaussian priors for Bayesian inversion, Simultaneous inference of periods and period-luminosity relations for Mira variable stars, Beyond Prediction: A Framework for Inference With Variational Approximations in Mixture Models, Solving inverse problems using data-driven models, Comment: Variational autoencoders as empirical Bayes, Unnamed Item, Variational inference with vine copulas: an efficient approach for Bayesian computer model calibration

Uses Software

• Stan
• PMTK
• ADVI
• PRMLT

Cites Work

• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• Finite sample Bernstein-von Mises theorem for semiparametric problems
• Asymptotic normality of maximum likelihood and its variational approximation for stochastic blockmodels
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• The Bernstein-von Mises theorem for the proportional hazard model
• The semiparametric Bernstein-von Mises theorem
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• On Bayesian supremum norm contraction rates
• Critical dimension in the semiparametric Bernstein-von Mises theorem
• Asymptotic normality and valid inference for Gaussian variational approximation
• Bernstein-von Mises theorems for Gaussian regression with increasing number of regressors
• Bayesian inverse problems with Gaussian priors
• A semiparametric Bernstein-von Mises theorem for Gaussian process priors
• Adaptive Bernstein-von Mises theorems in Gaussian white noise
• An analysis of Bayesian inference for nonparametric regression
• Bernstein-von Mises theorem for linear functionals of the density
• Generalized linear models
• Linear and generalized linear mixed models and their applications.
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models
• The Bernstein-von Mises theorem in semiparametric competing risks models
• On the consistency of Bayes estimates
• Consistency of Bayes estimates for nonparametric regression: normal theory
• Estimation and prediction for stochastic blockmodels for graphs with latent block structure
• On the Bernstein-von Mises theorem with infinite-dimensional parameters
• Bayesian nonparametrics
• A Bernstein-von Mises theorem in the nonparametric right-censoring model
• The Bernstein-von Mises theorem under misspecification
• Consistency of maximum-likelihood and variational estimators in the stochastic block model
• A Bernstein-von Mises theorem for discrete probability distributions
• On the Bernstein-von Mises phenomenon in the Gaussian white noise model
• An introduction to variational methods for graphical models
• Concentration of tempered posteriors and of their variational approximations
• Semiparametric Bernstein-von Mises theorem and bias, illustrated with Gaussian process priors
• A variational Bayes approach to variable selection
• On Variational Bayes Estimation and Variational Information Criteria for Linear Regression Models
• On the properties of variational approximations of Gibbs posteriors
• Explaining Variational Approximations
• Beyond Prediction: A Framework for Inference With Variational Approximations in Mixture Models
• Sampling-Based Approaches to Calculating Marginal Densities
• Graphical Models, Exponential Families, and Variational Inference
• Asymptotic Statistics
• On Profile Likelihood
• Gaussian Approximations for Probability Measures on $R^d$
• 10.1162/jmlr.2003.3.4-5.993
• Approximate Inference in Generalized Linear Mixed Models
• Stochastic Blockmodels for Directed Graphs
• On the Product of Diagonal Elements of a Positive Matrix
• Monte Carlo sampling methods using Markov chains and their applications
• Fundamentals of Nonparametric Bayesian Inference
• Convergence properties of a general algorithm for calculating variational Bayesian estimates for a normal mixture model
• 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
• Unnamed Item
• Unnamed Item