Stochastic black-box optimization using multi-fidelity score function estimator
Optimizing parameters of physics-based simulators is crucial in the design process of engineering and scientific systems. This becomes particularly challenging when the simulator is stochastic, computationally expensive, black-box and when a high-dimensional vector of parameters needs to be optimize...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad8e2b |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832544055082352640 |
|---|---|
| author | Atul Agrawal Kislaya Ravi Phaedon-Stelios Koutsourelakis Hans-Joachim Bungartz |
| author_facet | Atul Agrawal Kislaya Ravi Phaedon-Stelios Koutsourelakis Hans-Joachim Bungartz |
| author_sort | Atul Agrawal |
| collection | DOAJ |
| description | Optimizing parameters of physics-based simulators is crucial in the design process of engineering and scientific systems. This becomes particularly challenging when the simulator is stochastic, computationally expensive, black-box and when a high-dimensional vector of parameters needs to be optimized, as e.g. is the case in complex climate models that involve numerous interdependent variables and uncertain parameters. Many traditional optimization methods rely on gradient information, which is frequently unavailable in legacy black-box codes. To address these challenges, we present SCOUT-Nd ( S tochastic C onstrained O p t imization for N dimensions), a gradient-based algorithm that can be used on non-differentiable objectives. It can be combined with natural gradients in order to further enhance convergence properties. and it also incorporates multi-fidelity schemes and an adaptive selection of samples in order to minimize computational effort. We validate our approach using standard, benchmark problems, demonstrating its superior performance in parameter optimization compared to existing methods. Additionally, we showcase the algorithm’s efficacy in a complex real-world application, i.e. the optimization of a wind farm layout. |
| format | Article |
| id | doaj-art-5214d03bf7fc406b9d29d220c2839dae |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-5214d03bf7fc406b9d29d220c2839dae2025-02-03T10:58:23ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101502410.1088/2632-2153/ad8e2bStochastic black-box optimization using multi-fidelity score function estimatorAtul Agrawal0https://orcid.org/0000-0002-9101-359XKislaya Ravi1https://orcid.org/0000-0003-1927-7651Phaedon-Stelios Koutsourelakis2https://orcid.org/0000-0002-9345-759XHans-Joachim Bungartz3https://orcid.org/0000-0002-0171-0712Professorship of Data-Driven Materials Modelling, Technical University of Munich , Munich, GermanySchool of Computation, Information and Technology, Technical University of Munich , Munich, GermanyProfessorship of Data-Driven Materials Modelling, Technical University of Munich , Munich, GermanySchool of Computation, Information and Technology, Technical University of Munich , Munich, GermanyOptimizing parameters of physics-based simulators is crucial in the design process of engineering and scientific systems. This becomes particularly challenging when the simulator is stochastic, computationally expensive, black-box and when a high-dimensional vector of parameters needs to be optimized, as e.g. is the case in complex climate models that involve numerous interdependent variables and uncertain parameters. Many traditional optimization methods rely on gradient information, which is frequently unavailable in legacy black-box codes. To address these challenges, we present SCOUT-Nd ( S tochastic C onstrained O p t imization for N dimensions), a gradient-based algorithm that can be used on non-differentiable objectives. It can be combined with natural gradients in order to further enhance convergence properties. and it also incorporates multi-fidelity schemes and an adaptive selection of samples in order to minimize computational effort. We validate our approach using standard, benchmark problems, demonstrating its superior performance in parameter optimization compared to existing methods. Additionally, we showcase the algorithm’s efficacy in a complex real-world application, i.e. the optimization of a wind farm layout.https://doi.org/10.1088/2632-2153/ad8e2bblack-box optimizationmulti-fidelityscore function estimatorwindfarm layout optimizationoptimization under uncertainty |
| spellingShingle | Atul Agrawal Kislaya Ravi Phaedon-Stelios Koutsourelakis Hans-Joachim Bungartz Stochastic black-box optimization using multi-fidelity score function estimator Machine Learning: Science and Technology black-box optimization multi-fidelity score function estimator windfarm layout optimization optimization under uncertainty |
| title | Stochastic black-box optimization using multi-fidelity score function estimator |
| title_full | Stochastic black-box optimization using multi-fidelity score function estimator |
| title_fullStr | Stochastic black-box optimization using multi-fidelity score function estimator |
| title_full_unstemmed | Stochastic black-box optimization using multi-fidelity score function estimator |
| title_short | Stochastic black-box optimization using multi-fidelity score function estimator |
| title_sort | stochastic black box optimization using multi fidelity score function estimator |
| topic | black-box optimization multi-fidelity score function estimator windfarm layout optimization optimization under uncertainty |
| url | https://doi.org/10.1088/2632-2153/ad8e2b |
| work_keys_str_mv | AT atulagrawal stochasticblackboxoptimizationusingmultifidelityscorefunctionestimator AT kislayaravi stochasticblackboxoptimizationusingmultifidelityscorefunctionestimator AT phaedonstelioskoutsourelakis stochasticblackboxoptimizationusingmultifidelityscorefunctionestimator AT hansjoachimbungartz stochasticblackboxoptimizationusingmultifidelityscorefunctionestimator |