Log-Scale Shrinkage Priors and Adaptive Bayesian Global-Local Shrinkage Estimation

TL;DR

This paper introduces a novel class of log-scale priors for Bayesian global-local shrinkage, including the ultra-heavy tailed log-t prior, which enhances sparsity promotion, super-efficiency, and robustness in coefficient estimation.

Contribution

The paper proposes a new log-scale prior framework, including the log-t prior, unifying existing priors and improving adaptive shrinkage with theoretical guarantees.

Findings

Log-t prior always diverges at zero and has super-Cauchy tails.

Adaptive log-t procedure performs well across various sparsity levels.

Log-scale priors unify and extend standard shrinkage distributions.

Abstract

Global-local shrinkage hierarchies are an important innovation in Bayesian estimation. We propose the use of log-scale distributions as a novel basis for generating familes of prior distributions for local shrinkage hyperparameters. By varying the scale parameter one may vary the degree to which the prior distribution promotes sparsity in the coefficient estimates. By examining the class of distributions over the logarithm of the local shrinkage parameter that have log-linear, or sub-log-linear tails, we show that many standard prior distributions for local shrinkage parameters can be unified in terms of the tail behaviour and concentration properties of their corresponding marginal distributions over the coefficients $\beta_j$. We derive upper bounds on the rate of concentration around $|\beta_j|=0$, and the tail decay as $|\beta_j| \to \infty$, achievable by this wide class of prior distributions. We then propose a new type of ultra-heavy tailed prior, called the log-$t$ prior with the property that, irrespective of the choice of associated scale parameter, the marginal distribution always diverges at $\beta_j = 0$, and always possesses super-Cauchy tails. We develop results demonstrating when prior distributions with (sub)-log-linear tails attain Kullback--Leibler super-efficiency and prove that the log-$t$ prior distribution is always super-efficient. We show that the log-$t$ prior is less sensitive to misspecification of the global shrinkage parameter than the horseshoe or lasso priors. By incorporating the scale parameter of the log-scale prior distributions into the Bayesian hierarchy we derive novel adaptive shrinkage procedures. Simulations show that the adaptive log-$t$ procedure appears to always perform well, irrespective of the level of sparsity or signal-to-noise ratio of the underlying model.