Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 355 - Advanced Bayesian Topics (Part 4)
Type: Contributed
Date/Time: Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
Sponsor: Section on Bayesian Statistical Science
Abstract #318810
Title: Continuous shrinkage priors with dependence
Author(s): Toryn Schafer* and David S Matteson
Companies: Cornell University and Cornell University
Keywords: bayesian learning; spatial data; shrinkage prior; time series; dependence; generalized linear model
Abstract:

Continuous shrinkage priors have gained popularity in Bayesian models for learning sparse signals. Inducing dependence in the latent sparsity variables of a shrinkage prior allows for learning of locally smooth trends in space or time with potentially abrupt changes. For example, in time series modeling dependence in the dynamic shrinkage prior results in neighboring time points are likely to have similar sparsity. We present extensions of the dynamic shrinkage prior for broader applicability.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program