Shrinkage with shrunken shoulders: Gibbs sampling shrinkage model posteriors with guaranteed convergence rates

• Published in: Bayesian analysis Vol. 18; no. 2; pp. 367 - 390
• Main Authors: Nishimura, Akihiko, Suchard, Marc A
• Format: Journal Article
• Language: English
• Published: United States 01.06.2023
• Subjects: generalized linear model; secondary 62J07; Markov chain Monte Carlo; sparsity; Bayesian inference; Primary 60J20, 62F15; ergodicity

Use of continuous shrinkage priors - with a "spike" near zero and heavy-tails towards infinity - is an increasingly popular approach to induce sparsity in parameter estimates. When the parameters are only weakly identified by the likelihood, however, the posterior may end up with tails as...