Trust-Region Stochastic Optimization with Variance Reduction Technique
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912139218780160 |
|---|---|
| author | Zheng, Xinshou |
| author_facet | Zheng, Xinshou |
| contents | We propose a novel algorithm, TR-SVR, for solving unconstrained stochastic optimization problems. This method builds on the trust-region framework, which effectively balances local and global exploration in optimization tasks. TR-SVR incorporates variance reduction techniques to improve both computational efficiency and stability when addressing stochastic objective functions. The algorithm applies a sequential quadratic programming (SQP) approach within the trust-region framework, solving each subproblem approximately using variance-reduced gradient estimators. This integration ensures a robust convergence mechanism while maintaining efficiency, making TR-SVR particularly suitable for large-scale stochastic optimization challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00673 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trust-Region Stochastic Optimization with Variance Reduction Technique Zheng, Xinshou Optimization and Control We propose a novel algorithm, TR-SVR, for solving unconstrained stochastic optimization problems. This method builds on the trust-region framework, which effectively balances local and global exploration in optimization tasks. TR-SVR incorporates variance reduction techniques to improve both computational efficiency and stability when addressing stochastic objective functions. The algorithm applies a sequential quadratic programming (SQP) approach within the trust-region framework, solving each subproblem approximately using variance-reduced gradient estimators. This integration ensures a robust convergence mechanism while maintaining efficiency, making TR-SVR particularly suitable for large-scale stochastic optimization challenges. |
| title | Trust-Region Stochastic Optimization with Variance Reduction Technique |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2412.00673 |