Scaling laws for amplitude surrogates
This work applies known scaling laws to a specific domain (particle physics) to improve precision in amplitude surrogates, making it incremental.
The authors investigated scaling laws for neural network performance in the context of amplitude surrogates for particle physics, showing that scaling coefficients are connected to the number of external particles in the process, which helps achieve desired precision targets.
Scaling laws describing the dependence of neural network performance on the amount of training data, the spent compute, and the network size have emerged across a huge variety of machine learning task and datasets. In this work, we systematically investigate these scaling laws in the context of amplitude surrogates for particle physics. We show that the scaling coefficients are connected to the number of external particles of the process. Our results demonstrate that scaling laws are a useful tool to achieve desired precision targets.