Article Source

• An Introduction to Hamiltonian Monte Carlo Method for Sampling

An Introduction to Hamiltonian Monte Carlo Method for Sampling

• Nisheeth Vishnoi (Yale)
• URL
• Geometric Methods in Optimization and Sampling Boot Camp

Abstract

The goal of this talk is to introduce the Hamiltonian Monte Carlo method – a physics-inspired algorithm for sampling from Gibbs densities. We focus on the idealized case, where one can compute continuous trajectories exactly. We show that idealized HMC preserves the target density and we establish its convergence when f is strongly convex.