Convergence Rates of Variational Posterior Distributions
arXiv:1712.02519
Abstract
We study convergence rates of variational posterior distributions for nonparametric and high-dimensional inference. We formulate general conditions on prior, likelihood, and variational class that characterize the convergence rates. Under similar "prior mass and testing" conditions considered in the literature, the rate is found to be the sum of two terms. The first term stands for the convergence rate of the true posterior distribution, and the second term is contributed by the variational approximation error. For a class of priors that admit the structure of a mixture of product measures, we propose a novel prior mass condition, under which the variational approximation error of the mean-field class is dominated by convergence rate of the true posterior. We demonstrate the applicability of our general results for various models, prior distributions and variational classes by deriving convergence rates of the corresponding variational posteriors.
References in corpus (9)
- Simultaneous analysis of Lasso and Dantzig selector
- Rényi Divergence and Kullback-Leibler Divergence
- Rates of contraction of posterior distributions based on Gaussian process priors
- Asymptotic normality of maximum likelihood and its variational approximation for stochastic blockmodels
- Frequentist Consistency of Variational Bayes
- From -entropy to KL-entropy: Analysis of minimum information complexity density estimation
- On Bayesian supremum norm contraction rates
- Consistency of Variational Bayes Inference for Estimation and Model Selection in Mixtures
- A General Framework for Bayes Structured Linear Models