Unadjusted Langevin algorithm with multiplicative noise: total variation and Wasserstein bounds
DOI10.1214/22-aap1828zbMath1515.65032arXiv2012.14310OpenAlexW4297819871MaRDI QIDQ6103981
Publication date: 5 June 2023
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2012.14310
Malliavin calculusmultiplicative noiseweak errortotal variation distanceergodic diffusioninvariant distributionunadjusted Langevin algorithm\(L^1\)-Wasserstein distanceEuler scheme with decreasing step
Central limit and other weak theorems (60F05) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Stochastic approximation (62L20) Numerical solutions to stochastic differential and integral equations (65C30) Computational methods for ergodic theory (approximation of invariant measures, computation of Lyapunov exponents, entropy, etc.) (37M25)
Related Items (3)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Recursive computation of the invariant distribution of a diffusion
- Ergodicity of Markov semigroups with Hörmander type generators in infinite dimensions
- Regularization lemmas and convergence in total variation
- Large deviations and the Malliavin calculus
- Euler scheme and tempered distributions
- Computation of the invariant measure for a Lévy driven SDE: Rate of convergence
- Formulae for the derivatives of heat semigroups
- Analytic semigroups and degenerate elliptic operators with unbounded coefficients: A probabilistic approach
- Numerical probability. An introduction with applications to finance
- The law of the Euler scheme for stochastic differential equations. I: Convergence rate of the distribution function
- Long-time behaviour of degenerate diffusions: UFG-type SDEs and time-inhomogeneous hypoelliptic processes
- Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity
- Total variation distance between stochastic polynomials and invariance principles
- Exponential contraction in Wasserstein distances for diffusion semigroups with negative curvature
- A backward Itô-Ventzell formula with an application to stochastic interpolation
- Non-asymptotic Gaussian estimates for the recursive approximation of the invariant distribution of a diffusion
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- An adaptive scheme for the approximation of dissipative systems
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- Recursive computation of the invariant measure of a stochastic differential equation driven by a Lévy process
- A mixed-step algorithm for the approximation of the stationary regime of a diffusion
- Exponential convergence in Lp-Wasserstein distance for diffusion processes without uniformly dissipative drift
- The Malliavin Calculus and Related Topics
- Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $
- RECURSIVE COMPUTATION OF THE INVARIANT DISTRIBUTION OF A DIFFUSION: THE CASE OF A WEAKLY MEAN REVERTING DRIFT
- Sur quelques algorithmes récursifs pour les probabilités numériques
- Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes
- Metropolis-Type Annealing Algorithms for Global Optimization in $\mathbb{R}^d $
- Edgeworth type expansions for Euler schemes for stochastic differential equations.
- Analysis and Geometry of Markov Diffusion Operators
- Prediction, Learning, and Games
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Expansion of the global error for numerical schemes solving stochastic differential equations
- Uniform in time estimates for the weak error of the Euler method for SDEs and a pathwise approach to derivative estimates for diffusion semigroups
- Optimal Transport
- Spectral gap for spherically symmetric \(\log\)-concave probability measures, and beyond
This page was built for publication: Unadjusted Langevin algorithm with multiplicative noise: total variation and Wasserstein bounds
