Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.07795 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912187623145472 |
|---|---|
| author | Lian, Teng Hu, Jian-Qiang Wu, Yuhang Zheng, Zeyu |
| author_facet | Lian, Teng Hu, Jian-Qiang Wu, Yuhang Zheng, Zeyu |
| contents | Black-box optimization is often encountered for decision-making in complex systems management, where the knowledge of system is limited. Under these circumstances, it is essential to balance the utilization of new information with computational efficiency. In practice, decision-makers often face the dual tasks of optimization and statistical inference for the optimal performance, in order to achieve it with a high reliability. Our goal is to address the dual tasks in an online fashion. Wu et al (2022) [arXiv preprint: 2210.06737] point out that the sample average of performance estimates generated by the optimization algorithm needs not to admit a central limit theorem. We propose an algorithm that not only tackles this issue, but also provides an online consistent estimator for the variance of the performance. Furthermore, we characterize the convergence rate of the coverage probabilities of the asymptotic confidence intervals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07795 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Black-box Optimization with Simultaneous Statistical Inference for Optimal Performance Lian, Teng Hu, Jian-Qiang Wu, Yuhang Zheng, Zeyu Computation Machine Learning Black-box optimization is often encountered for decision-making in complex systems management, where the knowledge of system is limited. Under these circumstances, it is essential to balance the utilization of new information with computational efficiency. In practice, decision-makers often face the dual tasks of optimization and statistical inference for the optimal performance, in order to achieve it with a high reliability. Our goal is to address the dual tasks in an online fashion. Wu et al (2022) [arXiv preprint: 2210.06737] point out that the sample average of performance estimates generated by the optimization algorithm needs not to admit a central limit theorem. We propose an algorithm that not only tackles this issue, but also provides an online consistent estimator for the variance of the performance. Furthermore, we characterize the convergence rate of the coverage probabilities of the asymptotic confidence intervals. |
| title | Black-box Optimization with Simultaneous Statistical Inference for Optimal Performance |
| topic | Computation Machine Learning |
| url | https://arxiv.org/abs/2501.07795 |