Parameterized Machine Learning for High-Energy Physics
This incremental improvement simplifies training and enhances discrimination for high-energy physics applications, such as varying particle masses.
The paper tackles the problem of training multiple classifiers for varying physics parameters by introducing a parameterized classifier that includes physics parameters as inputs, enabling smooth interpolation and improved performance at intermediate values, even for deep learning tasks.
We investigate a new structure for machine learning classifiers applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters. The physics parameters represent a smoothly varying learning task, and the resulting parameterized classifier can smoothly interpolate between them and replace sets of classifiers trained at individual values. This simplifies the training process and gives improved performance at intermediate values, even for complex problems requiring deep learning. Applications include tools parameterized in terms of theoretical model parameters, such as the mass of a particle, which allow for a single network to provide improved discrimination across a range of masses. This concept is simple to implement and allows for optimized interpolatable results.