Optimal Convergence Rate of Hamiltonian Monte Carlo for Strongly Logconcave Distributions

05/07/2019
by   Zongchen Chen, et al.
0

We study Hamiltonian Monte Carlo (HMC) for sampling from a strongly logconcave density proportional to e^-f where f:R^d →R is μ-strongly convex and L-smooth (the condition number is κ = L/μ). We show that the relaxation time (inverse of the spectral gap) of ideal HMC is O(κ), improving on the previous best bound of O(κ^1.5); we complement this with an example where the relaxation time is Ω(κ). When implemented using a nearly optimal ODE solver, HMC returns an ε-approximate point in 2-Wasserstein distance using O((κ d)^0.5ε^-1) gradient evaluations per step and O((κ d)^1.5ε^-1) total time.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/27/2021

An Introduction to Hamiltonian Monte Carlo Method for Sampling

The goal of this article is to introduce the Hamiltonian Monte Carlo (HM...
research
10/13/2022

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

We study the convergence rate of discretized Riemannian Hamiltonian Mont...
research
02/10/2020

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...
research
05/01/2018

Coupling and Convergence for Hamiltonian Monte Carlo

Based on a new coupling approach, we prove that the transition step of t...
research
07/05/2022

Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time

Hamiltonian Monte Carlo (HMC) is a popular method in sampling. While the...
research
08/22/2023

Nonlinear Hamiltonian Monte Carlo its Particle Approximation

We present a nonlinear (in the sense of McKean) generalization of Hamilt...
research
11/29/2022

Penalized Langevin and Hamiltonian Monte Carlo Algorithms for Constrained Sampling

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

Please sign up or login with your details

Forgot password? Click here to reset