Log In Sign Up

Condition-number-independent Convergence Rate of Riemannian Hamiltonian Monte Carlo with Numerical Integrators

by   Yunbum Kook, et al.

We study the convergence rate of discretized Riemannian Hamiltonian Monte Carlo on sampling from distributions in the form of e^-f(x) on a convex set ℳ⊂ℝ^n. We show that for distributions in the form of e^-α^⊤x on a polytope with m constraints, the convergence rate of a family of commonly-used integrators is independent of ‖α‖_2 and the geometry of the polytope. In particular, the Implicit Midpoint Method (IMM) and the generalized Leapfrog integrator (LM) have a mixing time of O(mn^3) to achieve ϵ total variation distance to the target distribution. These guarantees are based on a general bound on the convergence rate for densities of the form e^-f(x) in terms of parameters of the manifold and the integrator. Our theoretical guarantee complements the empirical results of [KLSV22], which shows that RHMC with IMM can sample ill-conditioned, non-smooth and constrained distributions in very high dimension efficiently in practice.


page 1

page 2

page 3

page 4


Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space

We demonstrate for the first time that ill-conditioned, non-smooth, cons...

Convergence Rate of Riemannian Hamiltonian Monte Carlo and Faster Polytope Volume Computation

We give the first rigorous proof of the convergence of Riemannian Hamilt...

Optimal Convergence Rate of Hamiltonian Monte Carlo for Strongly Logconcave Distributions

We study Hamiltonian Monte Carlo (HMC) for sampling from a strongly logc...

Constrained Ensemble Langevin Monte Carlo

The classical Langevin Monte Carlo method looks for i.i.d. samples from ...

Penalized Langevin and Hamiltonian Monte Carlo Algorithms for Constrained Sampling

We consider the constrained sampling problem where the goal is to sample...

An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models

This technical report presents pseudo-code for a Riemannian manifold Ham...

Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo

We show that the gradient norm ∇ f(x) for x ∼(-f(x)), where f is strongl...