Recent Advances in the stochastic approximation methods and its application to stochastic dynamics
|
Organizer(s): |
Name:
|
Affiliation:
|
Country:
|
Lihu Xu
|
University of Macau
|
Macau
|
Peng Chen
|
Nanjing University of Aeronautics and Astronautics
|
Peoples Rep of China
|
Xinghu Jin
|
Hefei University of Technology
|
Peoples Rep of China
|
|
|
|
|
|
|
|
|
Introduction:
| | The session aims to bring together the leading experts worldwide to discuss the recent advances in Stein’s method and the related stochastic approximation theory, emphasizing three interconnected themes: 1) Advances in stable law approximations via Stein’s method, with explicit error bounds for systems exhibiting heavy-tailed behavior; 2) Advances in Stein’s method for diffusion approximation, which enables a tractable steady-state analysis of queueing systems through approximations of stationary measures for stochastic differential equations. 3) Advances in the Markovian framework for stochastic approximations of stochastic optimization algorithms—including SGD, SVRG, and momentum-based variants—to enable comparative analysis of their convergence dynamics. By synthesizing probabilistic tools with applications in optimization and queueing theory, we hope this session will demonstrate the unifying role of stochastic approximations in bridging theoretical innovation with practical challenges.
|
|
|
|
|
|
