Bibliographic Details
| Title: |
Decoupled Functional Central Limit Theorems for Two-Time-Scale Stochastic Approximation |
| Authors: |
Han, Yuze, Li, Xiang, Liang, Jiadong, Zhang, Zhihua |
| Publication Year: |
2024 |
| Collection: |
Mathematics
Statistics |
| Subject Terms: |
Mathematics - Probability, Mathematics - Optimization and Control, Statistics - Machine Learning |
| More Details: |
In two-time-scale stochastic approximation (SA), two iterates are updated at different rates, governed by distinct step sizes, with each update influencing the other. Previous studies have demonstrated that the convergence rates of the error terms for these updates depend solely on their respective step sizes, a property known as decoupled convergence. However, a functional version of this decoupled convergence has not been explored. Our work fills this gap by establishing decoupled functional central limit theorems for two-time-scale SA, offering a more precise characterization of its asymptotic behavior. To achieve these results, we leverage the martingale problem approach and establish tightness as a crucial intermediate step. Furthermore, to address the interdependence between different time scales, we introduce an innovative auxiliary sequence to eliminate the primary influence of the fast-time-scale update on the slow-time-scale update. |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2412.17070 |
| Accession Number: |
edsarx.2412.17070 |
| Database: |
arXiv |
