NIPS Proceedingsβ

Positive Curvature and Hamiltonian Monte Carlo

Part of: Advances in Neural Information Processing Systems 27 (NIPS 2014)

[PDF] [BibTeX] [Reviews]


Conference Event Type: Poster


The Jacobi metric introduced in mathematical physics can be used to analyze Hamiltonian Monte Carlo (HMC). In a geometrical setting, each step of HMC corresponds to a geodesic on a Riemannian manifold with a Jacobi metric. Our calculation of the sectional curvature of this HMC manifold allows us to see that it is positive in cases such as sampling from a high dimensional multivariate Gaussian. We show that positive curvature can be used to prove theoretical concentration results for HMC Markov chains.