Modification of Bayesian Optimization for Efficient Calibration of Simulation Models
| Autor: | Soh Koike, Ryota Narasaki, Masashi Tomita, Daiki Kiribuchi, Takeichiro Nishikawa, Satoru Yokota |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
010302 applied physics
Linear programming Computer science Calibration (statistics) Simulation modeling Bayesian optimization 02 engineering and technology Numerical models Parameter space 01 natural sciences Random search 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Algorithm Curse of dimensionality |
| Zdroj: | WSC |
| DOI: | 10.1109/wsc48552.2020.9384104 |
| Popis: | Simulation models contain many parameters that must be adjusted (calibrated) in advance to reduce the error between simulations and experimental results. Bayesian optimization is often applied to minimize error after only a few simulations. However, Bayesian optimization uses only error information, ignoring information on other simulation results. In this paper, we improve Bayesian optimization by utilizing both and show that other simulation results effectively reduce the dimensionality of the parameter space. In an evaluation using actual semiconductor simulation results, the proposed method reduces the number of simulations by 50% compared with random search and conventional Bayesian optimization. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|