Global Continuous Optimization with Error Bound and Fast Convergence
This paper considers global optimization with a black-box unknown objective function that can be non-convex and non-differentiable. Such a difficult optimization problem arises in many real-world applications, such as parameter tuning in machine learning, engineering design problem, and planning wit...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for the Advancement of Artificial Intelligence
2017
|
| Online Access: | http://hdl.handle.net/1721.1/107756 https://orcid.org/0000-0003-1839-7504 |
| _version_ | 1826197594013958144 |
|---|---|
| author | Maruyama, Yu Zheng, Xiaoyu Kawaguchi, Kenji |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Maruyama, Yu Zheng, Xiaoyu Kawaguchi, Kenji |
| author_sort | Maruyama, Yu |
| collection | MIT |
| description | This paper considers global optimization with a black-box unknown objective function that can be non-convex and non-differentiable. Such a difficult optimization problem arises in many real-world applications, such as parameter tuning in machine learning, engineering design problem, and planning with a complex physics simulator. This paper proposes a new global optimization algorithm, called Locally Oriented Global Optimization (LOGO), to aim for both fast convergence in practice and finite-time error bound in theory. The advantage and usage of the new algorithm are illustrated via theoretical analysis and an experiment conducted with 11 benchmark test functions. Further, we modify the LOGO algorithm to specifically solve a planning problem via policy search with continuous state/action space and long time horizon while maintaining its finite-time error bound. We apply the proposed planning method to accident management of a nuclear power plant. The result of the application study demonstrates the practical utility of our method. |
| first_indexed | 2024-09-23T10:50:20Z |
| format | Article |
| id | mit-1721.1/107756 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:50:20Z |
| publishDate | 2017 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | mit-1721.1/1077562022-09-27T15:23:00Z Global Continuous Optimization with Error Bound and Fast Convergence Maruyama, Yu Zheng, Xiaoyu Kawaguchi, Kenji Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Kawaguchi, Kenji This paper considers global optimization with a black-box unknown objective function that can be non-convex and non-differentiable. Such a difficult optimization problem arises in many real-world applications, such as parameter tuning in machine learning, engineering design problem, and planning with a complex physics simulator. This paper proposes a new global optimization algorithm, called Locally Oriented Global Optimization (LOGO), to aim for both fast convergence in practice and finite-time error bound in theory. The advantage and usage of the new algorithm are illustrated via theoretical analysis and an experiment conducted with 11 benchmark test functions. Further, we modify the LOGO algorithm to specifically solve a planning problem via policy search with continuous state/action space and long time horizon while maintaining its finite-time error bound. We apply the proposed planning method to accident management of a nuclear power plant. The result of the application study demonstrates the practical utility of our method. 2017-03-28T17:19:32Z 2017-03-28T17:19:32Z 2016-06 2015-03 Article http://purl.org/eprint/type/JournalArticle 1943-5037 1076-9757 http://hdl.handle.net/1721.1/107756 Kawaguchi, Kenji, Yu Maruyama and Xiaoyu Zheng. "Global Continuous Optimization with Error Bound and Fast Convergence." Journal of Articial Intelligence Research 56 (2016): 153-195. https://orcid.org/0000-0003-1839-7504 en_US http://dx.doi.org/10.1613/jair.4742 Journal of Artificial Intelligence Research Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Association for the Advancement of Artificial Intelligence AAAI |
| spellingShingle | Maruyama, Yu Zheng, Xiaoyu Kawaguchi, Kenji Global Continuous Optimization with Error Bound and Fast Convergence |
| title | Global Continuous Optimization with Error Bound and Fast Convergence |
| title_full | Global Continuous Optimization with Error Bound and Fast Convergence |
| title_fullStr | Global Continuous Optimization with Error Bound and Fast Convergence |
| title_full_unstemmed | Global Continuous Optimization with Error Bound and Fast Convergence |
| title_short | Global Continuous Optimization with Error Bound and Fast Convergence |
| title_sort | global continuous optimization with error bound and fast convergence |
| url | http://hdl.handle.net/1721.1/107756 https://orcid.org/0000-0003-1839-7504 |
| work_keys_str_mv | AT maruyamayu globalcontinuousoptimizationwitherrorboundandfastconvergence AT zhengxiaoyu globalcontinuousoptimizationwitherrorboundandfastconvergence AT kawaguchikenji globalcontinuousoptimizationwitherrorboundandfastconvergence |