Hamiltonian Monte Carlo for Hierarchical Models

TL;DR

This paper explores the application of Hamiltonian Monte Carlo to hierarchical models, demonstrating its ability to address inference pathologies and improve efficiency in complex statistical problems.

Contribution

It introduces a novel application of Hamiltonian Monte Carlo specifically tailored for hierarchical models, overcoming common inference challenges.

Findings

HMC effectively mitigates pathologies in hierarchical models

Improved sampling efficiency demonstrated in practical applications

Addresses limitations of traditional inference methods for complex models

Abstract

Hierarchical modeling provides a framework for modeling the complex interactions typical of problems in applied statistics. By capturing these relationships, however, hierarchical models also introduce distinctive pathologies that quickly limit the efficiency of most common methods of in- ference. In this paper we explore the use of Hamiltonian Monte Carlo for hierarchical models and demonstrate how the algorithm can overcome those pathologies in practical applications.