Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations

DOI10.1007/s00245-022-09854-3zbMath1500.60030arXiv2106.04357OpenAlexW3166294970WikidataQ115388182 ScholiaQ115388182MaRDI QIDQ2128624

Jianya Lu, Peng Chen, Lihu Xu

Publication date: 22 April 2022

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.04357

zbMATH Keywords

Malliavin calculusstochastic delay differential equationsrefined Lindeberg principlestochastic variance reduced gradient Langevin dynamicsWasserstein-1 distance

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Approximation methods and heuristics in mathematical programming (90C59) Applications of stochastic analysis (to PDEs, etc.) (60H30) Stochastic calculus of variations and the Malliavin calculus (60H07)

Related Items (2)

Rate of homogenization for fully-coupled McKean–Vlasov SDEs ⋮ Approximation of the invariant measure of stable SDEs by an Euler-Maruyama scheme

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Exponential growth rate for a singular linear stochastic delay differential equation
• Polynomial chaos and scaling limits of disordered systems
• Random matrices: universality of local eigenvalue statistics
• On the empirical spectral distribution for matrices with long memory and independent rows
• A generalization of the Lindeberg principle
• Stein estimation for the drift of Gaussian processes using the Malliavin calculus
• On the diffusion approximation of nonconvex stochastic gradient descent
• Introduction to the numerical analysis of stochastic delay differential equations
• Regularity of invariant measures on finite and infinite dimensional spaces and applications
• Applications of Malliavin calculus to Monte Carlo methods in finance
• Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation
• Semigroups of stochastic gradient descent and online principal component analysis: properties and diffusion approximations
• The tamed unadjusted Langevin algorithm
• Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Approximation to stable law by the Lindeberg principle
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Approximation of the invariant measure with an Euler scheme for stochastic PDEs driven by space-time white noise
• Ergodicity for functional stochastic differential equations and applications
• Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
• Ergodicity of the 2D Navier-Stokes equations with degenerate stochastic forcing
• Malliavin Monte Carlo Greeks for jump diffusions
• Bismut formula for Lions derivative of distribution-path dependent SDEs
• Asymptotic Analysis for Functional Stochastic Differential Equations
• Flows of homeomorphisms of stochastic differential equations with measurable drift
• Elliptic and parabolic equations in with coefficients having polynomial growth
• On the fast convergence of random perturbations of the gradient flow
• Applications of the Lindeberg Principle in Communications and Statistical Learning
• Sensitivity Analysis Using Itô--Malliavin Calculus and Martingales, and Application to Stochastic Optimal Control
• Elliptic operators on \(\mathbb{R}^d\) with unbounded coefficients

This page was built for publication: Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations