Chen, Peng and Lu, Jianya and Xu, Lihu (2022) Approximation to Stochastic Variance Reduced Gradient Langevin Dynamics by Stochastic Delay Differential Equations. Applied Mathematics and Optimization, 85 (2). DOI https://doi.org/10.1007/s00245-022-09854-3
Chen, Peng and Lu, Jianya and Xu, Lihu (2022) Approximation to Stochastic Variance Reduced Gradient Langevin Dynamics by Stochastic Delay Differential Equations. Applied Mathematics and Optimization, 85 (2). DOI https://doi.org/10.1007/s00245-022-09854-3
Chen, Peng and Lu, Jianya and Xu, Lihu (2022) Approximation to Stochastic Variance Reduced Gradient Langevin Dynamics by Stochastic Delay Differential Equations. Applied Mathematics and Optimization, 85 (2). DOI https://doi.org/10.1007/s00245-022-09854-3
Abstract
We study in this paper weak approximations in Wasserstein-1 distance to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations, and obtain uniform error bounds. Our approach is via Malliavin calculus and a refined Lindeberg principle.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | stochastic variance reduced gradient Langevin dynamics (SVRG-LD), stochastic delay differential equations (SDDEs), Malliavin calculus, Refined Lindeberg principle, Wasserstein-1 distance |
| Divisions: | Faculty of Science and Health Faculty of Science and Health > Mathematics, Statistics and Actuarial Science, School of |
| SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
| Depositing User: | Unnamed user with email elements@essex.ac.uk |
| Date Deposited: | 02 Nov 2022 11:55 |
| Last Modified: | 30 Oct 2024 15:51 |
| URI: | http://repository.essex.ac.uk/id/eprint/33802 |
Available files
Filename: 2106.04357.pdf