The computational asymptotics of Gaussian variational inference and the Laplace approximation

DOI10.1007/s11222-022-10125-yzbMath1495.62015arXiv2104.05886OpenAlexW4292074665WikidataQ114223422 ScholiaQ114223422MaRDI QIDQ2172111

Trevor Campbell, Zuheng Xu

Publication date: 15 September 2022

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.05886

zbMATH Keywords

Bayesian statisticsLaplace approximationvariational inferenceBernstein-von Misescomputational asymptotics

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Convex programming (90C25)

Uses Software

• PMTK
• AdaGrad
• Adam
• ADVI

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
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Asymptotic normality and valid inference for Gaussian variational approximation
• Markov chains and stochastic stability
• Asymptotic equivalence of empirical likelihood and Bayesian MAP
• General state space Markov chains and MCMC algorithms
• Maximum a posteriori estimators as a limit of Bayes estimators
• Convergence rates of posterior distributions.
• Rates of convergence of posterior distributions.
• Weak convergence and empirical processes. With applications to statistics
• The Bernstein-von Mises theorem under misspecification
• On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
• \(\alpha\)-variational inference with statistical guarantees
• Concentration of tempered posteriors and of their variational approximations
• Convergence rates of variational posterior distributions
• Minimization of functions having Lipschitz continuous first partial derivatives
• Laplace Approximation in High-Dimensional Bayesian Regression
• Rényi Divergence and Kullback-Leibler Divergence
• Quasi-Concave Programming
• Sampling-Based Approaches to Calculating Marginal Densities
• Graphical Models, Exponential Families, and Variational Inference
• What is invexity?
• Criteria for quasi-convexity and pseudo-convexity: Relationships and comparisons
• Asymptotic Statistics
• Gradient Convergence in Gradient methods with Errors
• A Study on Invariance of $f$-Divergence and Its Application to Speech Recognition
• On Choosing and Bounding Probability Metrics
• Frequentist Consistency of Variational Bayes
• Advanced Lectures on Machine Learning
• Asymptotic Properties of Non-Linear Least Squares Estimators
• Monte Carlo sampling methods using Markov chains and their applications
• Local optima smoothing for global optimization
• A Stochastic Approximation Method
• Convex analysis and monotone operator theory in Hilbert spaces

This page was built for publication: The computational asymptotics of Gaussian variational inference and the Laplace approximation