Sampling with Barriers: Faster Mixing via Lewis Weights

03/01/2023
by   Khashayar Gatmiry, et al.
0

We analyze Riemannian Hamiltonian Monte Carlo (RHMC) for sampling a polytope defined by m inequalities in ^n endowed with the metric defined by the Hessian of a convex barrier function. The advantage of RHMC over Euclidean methods such as the ball walk, hit-and-run and the Dikin walk is in its ability to take longer steps. However, in all previous work, the mixing rate has a linear dependence on the number of inequalities. We introduce a hybrid of the Lewis weights barrier and the standard logarithmic barrier and prove that the mixing rate for the corresponding RHMC is bounded by Õ(m^1/3n^4/3), improving on the previous best bound of Õ(mn^2/3) (based on the log barrier). This continues the general parallels between optimization and sampling, with the latter typically leading to new tools and more refined analysis. To prove our main results, we have to overcomes several challenges relating to the smoothness of Hamiltonian curves and the self-concordance properties of the barrier. In the process, we give a general framework for the analysis of Markov chains on Riemannian manifolds, derive new smoothness bounds on Hamiltonian curves, a central topic of comparison geometry, and extend self-concordance to the infinity norm, which gives sharper bounds; these properties appear to be of independent interest.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2017

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

We give the first rigorous proof of the convergence of Riemannian Hamilt...
research
10/21/2022

Barrier Hamiltonian Monte Carlo

In this paper, we propose Barrier Hamiltonian Monte Carlo (BHMC), a vers...
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
04/22/2022

Convergence of the Riemannian Langevin Algorithm

We study the Riemannian Langevin Algorithm for the problem of sampling f...
research
12/01/2022

Hit-and-run mixing via localization schemes

We analyze the hit-and-run algorithm for sampling uniformly from an isot...
research
11/13/2019

Strong Self-Concordance and Sampling

Motivated by the Dikin walk, we develop aspects of an interior-point the...
research
05/05/2019

Faster algorithms for polytope rounding, sampling, and volume computation via a sublinear "Ball Walk"

We study the problem of "isotropically rounding" a polytope K⊆R^n, that ...

Please sign up or login with your details

Forgot password? Click here to reset