A note on simulation methods for the Dirichlet-Laplace prior
By: Luis Gruber , Gregor Kastner , Anirban Bhattacharya and more
Potential Business Impact:
Fixes computer math to get better results.
Bhattacharya et al. (2015, Journal of the American Statistical Association 110(512): 1479-1490) introduce a novel prior, the Dirichlet-Laplace (DL) prior, and propose a Markov chain Monte Carlo (MCMC) method to simulate posterior draws under this prior in a conditionally Gaussian setting. The original algorithm samples from conditional distributions in the wrong order, i.e., it does not correctly sample from the joint posterior distribution of all latent variables. This note details the issue and provides two simple solutions: A correction to the original algorithm and a new algorithm based on an alternative, yet equivalent, formulation of the prior. This corrigendum does not affect the theoretical results in Bhattacharya et al. (2015).
Similar Papers
On the Posterior Computation Under the Dirichlet-Laplace Prior
Methodology
Fixes computer math for better data guesses.
Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
Machine Learning (CS)
Improves image guessing by learning from noise.
A Metropolis-Adjusted Langevin Algorithm for Sampling Jeffreys Prior
Systems and Control
Lets computers learn from vague information better.