Optimal Data Generation in Multi-Dimensional Parameter Spaces, using Bayesian Optimization
This work addresses the problem of data scarcity for researchers in scientific domains where data collection is costly, offering an incremental improvement over existing methods.
The paper tackles the challenge of acquiring large datasets for training machine learning models in resource-intensive scientific fields by proposing a method to construct a minimal yet informative database using Gaussian process regression and Bayesian optimization. The results show that models trained on this database consistently outperform those using traditional approaches, achieving high accuracy with significantly fewer data points.
Acquiring a substantial number of data points for training accurate machine learning (ML) models is a big challenge in scientific fields where data collection is resource-intensive. Here, we propose a novel approach for constructing a minimal yet highly informative database for training ML models in complex multi-dimensional parameter spaces. To achieve this, we mimic the underlying relation between the output and input parameters using Gaussian process regression (GPR). Using a set of known data, GPR provides predictive means and standard deviation for the unknown data. Given the predicted standard deviation by GPR, we select data points using Bayesian optimization to obtain an efficient database for training ML models. We compare the performance of ML models trained on databases obtained through this method, with databases obtained using traditional approaches. Our results demonstrate that the ML models trained on the database obtained using Bayesian optimization approach consistently outperform the other two databases, achieving high accuracy with a significantly smaller number of data points. Our work contributes to the resource-efficient collection of data in high-dimensional complex parameter spaces, to achieve high precision machine learning predictions.