Geometric ergodicity of SGLD via reflection coupling
From MaRDI portal
Publication:6649861
DOI10.1142/S0219493724500357MaRDI QIDQ6649861
Lei Li, Jian-Guo Liu, Yuliang Wang
Publication date: 6 December 2024
Published in: Stochastics and Dynamics (Search for Journal in Brave)
Wasserstein distanceEuler-Maruyama schemereflection couplingrandom batchstochastic gradient Langevin dynamics algorithm
Ergodicity, mixing, rates of mixing (37A25) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Reflection couplings and contraction rates for diffusions
- Reflection coupling and Wasserstein contractivity without convexity
- Coupling of multidimensional diffusions by reflection
- Vlasov equations
- Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
- Semi-martingale inequalities via the Garsia-Rodemich-Rumsey lemma, and applications to local times
- Optimum bounds for the distributions of martingales in Banach spaces
- Semigroups of stochastic gradient descent and online principal component analysis: properties and diffusion approximations
- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
- Random batch methods (RBM) for interacting particle systems
- Couplings and quantitative contraction rates for Langevin dynamics
- L\({}^ p\) estimates on iterated stochastic integrals
- Coupling and convergence for Hamiltonian Monte Carlo
- Nonasymptotic bounds for sampling algorithms without log-concavity
- Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
- Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes
- High-Dimensional Probability
- An elementary approach to uniform in time propagation of chaos
- On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
- A Stochastic Approximation Method
- Optimal Transport
This page was built for publication: Geometric ergodicity of SGLD via reflection coupling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6649861)