Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.15866 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916494069202944 |
|---|---|
| author | Smirnov, V. N. Kazistova, K. M. Sudakov, I. A. Leplat, V. Gasnikov, A. V. Lobanov, A. V. |
| author_facet | Smirnov, V. N. Kazistova, K. M. Sudakov, I. A. Leplat, V. Gasnikov, A. V. Lobanov, A. V. |
| contents | Black-box optimization, a rapidly growing field, faces challenges due to limited knowledge of the objective function's internal mechanisms. One promising approach to address this is the Stochastic Order Oracle Concept. This concept, similar to other Order Oracle Concepts, relies solely on relative comparisons of function values without requiring access to the exact values. This paper presents a novel, improved estimation of the covariance matrix for the asymptotic convergence of the Stochastic Order Oracle Concept. Our work surpasses existing research in this domain by offering a more accurate estimation of asymptotic convergence rate. Finally, numerical experiments validate our theoretical findings, providing strong empirical support for our proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15866 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ruppert-Polyak averaging for Stochastic Order Oracle Smirnov, V. N. Kazistova, K. M. Sudakov, I. A. Leplat, V. Gasnikov, A. V. Lobanov, A. V. Machine Learning Black-box optimization, a rapidly growing field, faces challenges due to limited knowledge of the objective function's internal mechanisms. One promising approach to address this is the Stochastic Order Oracle Concept. This concept, similar to other Order Oracle Concepts, relies solely on relative comparisons of function values without requiring access to the exact values. This paper presents a novel, improved estimation of the covariance matrix for the asymptotic convergence of the Stochastic Order Oracle Concept. Our work surpasses existing research in this domain by offering a more accurate estimation of asymptotic convergence rate. Finally, numerical experiments validate our theoretical findings, providing strong empirical support for our proposed approach. |
| title | Ruppert-Polyak averaging for Stochastic Order Oracle |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.15866 |