Implicit Langevin Algorithms for Sampling From Log-concave Densities
arXiv:1903.12322
Abstract
For sampling from a log-concave density, we study implicit integrators resulting from -method discretization of the overdamped Langevin diffusion stochastic differential equation. Theoretical and algorithmic properties of the resulting sampling methods for and a range of step sizes are established. Our results generalize and extend prior works in several directions. In particular, for , we prove geometric ergodicity and stability of the resulting methods for all step sizes. We show that obtaining subsequent samples amounts to solving a strongly-convex optimization problem, which is readily achievable using one of numerous existing methods. Numerical examples supporting our theoretical analysis are also presented.
References in corpus (7)
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- Austerity in MCMC Land: Cutting the Metropolis-Hastings Budget
- Underdamped Langevin MCMC: A non-asymptotic analysis
- Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
- Convergence of Langevin MCMC in KL-divergence
- Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
- DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization