Positive Curvature and Hamiltonian Monte Carlo

Christof Seiler, Simon Rubinstein-Salzedo, Susan P. Holmes

Abstract

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.
BibTeX
@inproceedings{seiler2014positive,
  author = {Christof Seiler and Simon Rubinstein-Salzedo and Susan P. Holmes},
  title = {{Positive Curvature and Hamiltonian Monte Carlo}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2014},
}

Loading related content...

Figure