| Primal-Dual ε-Subgradient Method for Distributed Optimization |
| |
| 作者姓名： | ZHU Kui TANG Yutao |
| |
| 作者单位： | School of Artificial Intelligence, Beijing University of Posts and Telecommunications |
| |
| 基金项目： | supported by the National Natural Science Foundation of China under Grant No. 61973043; |
| |
| 摘 要： | This paper studies the distributed optimization problem when the objective functions might be nondifferentiable and subject to heterogeneous set constraints. Unlike existing subgradient methods, the authors focus on the case when the exact subgradients of the local objective functions can not be accessed by the agents. To solve this problem, the authors propose a projected primaldual dynamics using only the objective function’s approximate subgradients. The authors first prove that the formulate...
|
|
