Sequential Quadratic Optimization for Solving Expectation Equality Constrained Stochastic Optimization Problems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914391711023104 |
|---|---|
| author | Shen, Haoming Zeng, Yang Zhou, Baoyu |
| author_facet | Shen, Haoming Zeng, Yang Zhou, Baoyu |
| contents | A sequential quadratic programming method is designed for solving general smooth nonlinear stochastic optimization problems subject to expectation equality constraints. We consider the setting where the objective and constraint function values, as well as their derivatives, are not directly available. The algorithm applies an adaptive step size policy and only relies on objective gradient estimates, constraint function estimates, and constraint derivative estimates to update iterates. Both asymptotic and non-asymptotic convergence properties of the algorithm are analyzed. Under reasonable assumptions, the algorithm generates a sequence of iterates whose first-order stationary measure diminishes in expectation. In addition, we identify the iteration and sample complexity for obtaining a first-order $\varepsilon$-stationary iterate in expectation. The results of numerical experiments demonstrate the efficiency and efficacy of our proposed algorithm compared to a penalty method and an augmented Lagrangian method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09490 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sequential Quadratic Optimization for Solving Expectation Equality Constrained Stochastic Optimization Problems Shen, Haoming Zeng, Yang Zhou, Baoyu Optimization and Control A sequential quadratic programming method is designed for solving general smooth nonlinear stochastic optimization problems subject to expectation equality constraints. We consider the setting where the objective and constraint function values, as well as their derivatives, are not directly available. The algorithm applies an adaptive step size policy and only relies on objective gradient estimates, constraint function estimates, and constraint derivative estimates to update iterates. Both asymptotic and non-asymptotic convergence properties of the algorithm are analyzed. Under reasonable assumptions, the algorithm generates a sequence of iterates whose first-order stationary measure diminishes in expectation. In addition, we identify the iteration and sample complexity for obtaining a first-order $\varepsilon$-stationary iterate in expectation. The results of numerical experiments demonstrate the efficiency and efficacy of our proposed algorithm compared to a penalty method and an augmented Lagrangian method. |
| title | Sequential Quadratic Optimization for Solving Expectation Equality Constrained Stochastic Optimization Problems |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2503.09490 |