Rapid Mixing of Hamiltonian Monte Carlo on Strongly Log-Concave Distributions

08/23/2017
by   Oren Mangoubi, et al.
0

We obtain several quantitative bounds on the mixing properties of the Hamiltonian Monte Carlo (HMC) algorithm for a strongly log-concave target distribution π on R^d, showing that HMC mixes quickly in this setting. One of our main results is a dimension-free bound on the mixing of an "ideal" HMC chain, which is used to show that the usual leapfrog implementation of HMC can sample from π using only O(d^1/4) gradient evaluations. This dependence on dimension is sharp, and our results significantly extend and improve previous quantitative bounds on the mixing of HMC.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset