High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion
From MaRDI portal
Publication:2233568
DOI10.1214/21-EJS1888zbMath1471.65010arXiv2007.05455MaRDI QIDQ2233568
Publication date: 11 October 2021
Published in: Electronic Journal of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2007.05455
Monte Carlo methods (65C05) Computational methods for problems pertaining to probability theory (60-08) Diffusion processes (60J60)
Related Items
Complexity of zigzag sampling algorithm for strongly log-concave distributions ⋮ Optimal friction matrix for underdamped Langevin sampling ⋮ High Order Splitting Methods for SDEs Satisfying a Commutativity Condition ⋮ Unnamed Item ⋮ Mixing time guarantees for unadjusted Hamiltonian Monte Carlo ⋮ Wasserstein-based methods for convergence complexity analysis of MCMC with applications
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data
- A patch that imparts unconditional stability to explicit integrators for Langevin-like equations
- Degenerate Fokker-Planck equations: Bismut formula, gradient estimate and Harnack inequality
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
- Short and long time behavior of the Fokker-Planck equation in a confining potential and applications
- On \(\mathcal{H}^1\) and entropic convergence for contractive PDMP
- Duality on gradient estimates and Wasserstein controls
- On the long time behavior of the TCP window size process
- Ricci curvature of Markov chains on metric spaces
- Hypocoercivity for kinetic equations with linear relaxation terms
- Rapid mixing of geodesic walks on manifolds with positive curvature
- Hypocoercivity in metastable settings and kinetic simulated annealing
- One-shot coupling for certain stochastic recursive sequences.
- Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
- Is there an analog of Nesterov acceleration for gradient-based MCMC?
- On sampling from a log-concave density using kinetic Langevin diffusions
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Couplings and quantitative contraction rates for Langevin dynamics
- Long-time behaviour and propagation of chaos for mean field kinetic particles
- Exponential ergodicity of the bouncy particle sampler
- Coupling and convergence for Hamiltonian Monte Carlo
- Geometric L2 and L1 convergence are equivalent for reversible Markov chains
- Pathwise accuracy and ergodicity of metropolized integrators for SDEs
- Hypocoercivity
- Rational Construction of Stochastic Numerical Methods for Molecular Sampling
- Analysis and Geometry of Markov Diffusion Operators
- Trend to equilibrium and particle approximation for a weakly selfconsistent Vlasov-Fokker-Planck equation
- Kinetic walks for sampling
- Convergence rate of Riemannian Hamiltonian Monte Carlo and faster polytope volume computation
- Partial differential equations and stochastic methods in molecular dynamics
- Optimal Transport
- A function space HMC algorithm with second order Langevin diffusion limit
