New directions for surrogate models and differentiable programming for High Energy Physics detector simulation
High Energy Physics - Phenomenology
2022-03-21 v1 Machine Learning
High Energy Physics - Experiment
Computational Physics
Instrumentation and Detectors
Abstract
The computational cost for high energy physics detector simulation in future experimental facilities is going to exceed the current available resources. To overcome this challenge, new ideas on surrogate models using machine learning methods are being explored to replace computationally expensive components. Additionally, differentiable programming has been proposed as a complementary approach, providing controllable and scalable simulation routines. In this document, new and ongoing efforts for surrogate models and differential programming applied to detector simulation are discussed in the context of the 2021 Particle Physics Community Planning Exercise (`Snowmass').
Keywords
Cite
@article{arxiv.2203.08806,
title = {New directions for surrogate models and differentiable programming for High Energy Physics detector simulation},
author = {Andreas Adelmann and Walter Hopkins and Evangelos Kourlitis and Michael Kagan and Gregor Kasieczka and Claudius Krause and David Shih and Vinicius Mikuni and Benjamin Nachman and Kevin Pedro and Daniel Winklehner},
journal= {arXiv preprint arXiv:2203.08806},
year = {2022}
}
Comments
contribution to Snowmass 2021