论文标题
高精度实验的高斯工艺和贝叶斯优化
Gaussian Processes and Bayesian Optimization for High Precision Experiments
论文作者
论文摘要
高精度测量需要最佳的设置和分析工具才能实现持续改进。需要以高精度和已知的不确定性建模系统校正以重建潜在的物理现象。为此，我们介绍了用于建模实验和使用贝叶斯优化的高斯工艺，以电子能量探测器的示例，以实现最佳性能。我们演示了该方法的优势和大概具有大数据集的物理应用的随机变化高斯过程，从而为当前问题提供了新的解决方案。
High-precision measurements require optimal setups and analysis tools to achieve continuous improvements. Systematic corrections need to be modeled with high accuracy and known uncertainty to reconstruct underlying physical phenomena. To this end, we present Gaussian processes for modeling experiments and usage with Bayesian optimization, on the example of an electron energy detector, achieving optimal performance. We demonstrate the method's strengths and outline stochastic variational Gaussian processes for physics applications with large data sets, enabling new solutions for current problems.
