Gibbs posterior concentration rates under sub-exponential type losses

DOI10.3150/22-BEJ1491MaRDI QIDQ2692523

Ryan Martin, Nicholas Syring

Publication date: 22 March 2023

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.04505

zbMATH Keywords

classificationmodel misspecificationM-estimationhigh-dimensional problemgeneralized Bayes

Mathematics Subject Classification ID

Parametric inference (62Fxx) Artificial intelligence (68Txx) Nonparametric inference (62Gxx)

Related Items (4)

Generalized Bayes approach to inverse problems with model misspecification ⋮ Bernstein-von Mises theorem and misspecified models: a review ⋮ User-friendly Introduction to PAC-Bayes Bounds ⋮ Adaptive variational Bayes: optimality, computation and applications

Uses Software

• robustbase

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Empirical Bayes posterior concentration in sparse high-dimensional linear models
• On posterior concentration in misspecified models
• Nonparametric binary regression using a Gaussian process prior
• PAC-Bayesian bounds for randomized empirical risk minimizers
• Risk bounds for statistical learning
• Bayesian linear regression with sparse priors
• Gibbs posterior for variable selection in high-dimensional classification and data mining
• \(M\)-estimation, convexity and quantiles
• An MCMC approach to classical estimation.
• Smooth discrimination analysis
• Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing it
• Convergence rates of posterior distributions.
• Rates of convergence of posterior distributions.
• Limited information likelihood and Bayesian analysis
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• Optimal aggregation of classifiers in statistical learning.
• Asymptotical minimax recovery of sets with smooth boundaries
• The consistency of posterior distributions in nonparametric problems
• Gibbs posterior inference on multivariate quantiles
• Robust and rate-optimal Gibbs posterior inference on the boundary of a noisy image
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Gibbs posterior inference on the minimum clinically important difference
• Misspecification in infinite-dimensional Bayesian statistics
• On the properties of variational approximations of Gibbs posteriors
• Bayesian Estimation and Comparison of Moment Condition Models
• The Safe Bayesian
• Adaptive Bayesian Procedures Using Random Series Priors
• Minimum clinically important difference in medical studies
• Information-theoretic upper and lower bounds for statistical estimation
• A theory of the learnable
• Asymptotic Statistics
• Calibrating general posterior credible regions
• General Bayesian updating and the loss-likelihood bootstrap
• A General Framework for Updating Belief Distributions
• OUP accepted manuscript
• Robust Statistics
• Robust Statistics

This page was built for publication: Gibbs posterior concentration rates under sub-exponential type losses