Implicit Langevin Algorithms for Sampling From Log-concave Densities
Preprint
Abstract
For sampling from a log-concave density, we study implicit integrators resulting from $\theta$-method discretization of the overdamped Langevin diffusion stochastic differential equation. Theoretical and algorithmic properties of the resulting sampling methods for $ \theta \in [0,1] $ and a range of step sizes are established. Our results generalize and extend prior works in several directions. In particular, for $\theta\ge1/2$, 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.
Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Informed sub-sampling MCMC: approximate Bayesian inference for large datasetsStatistics and Computing, 2018
- Kernel Mean Embedding of Distributions: A Review and BeyondFoundations and Trends in Machine Learning, 2017
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithmThe Annals of Applied Probability, 2017
- Proximal Markov chain Monte Carlo algorithmsStatistics and Computing, 2015
- Weak backward error analysis for overdamped Langevin processesIMA Journal of Numerical Analysis, 2014
- Riemann Manifold Langevin and Hamiltonian Monte Carlo MethodsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2011
- Stability of Partially Implicit Langevin Schemes and Their MCMC VariantsMethodology and Computing in Applied Probability, 2010
- Computer Methods for Ordinary Differential Equations and Differential-Algebraic Equations1998
- Local Linearization method for the numerical solution of stochastic differential equationsAnnals of the Institute of Statistical Mathematics, 1996
- Population correlation matrices for sampling experimentsCommunications in Statistics - Simulation and Computation, 1978