Machine learning has become an essential tool in jet physics. Due to their complex, high-dimensional nature, jets can be explored holistically by neural networks in ways that are not possible manually. However, innovations in all areas of jet physics are proceeding in parallel. We show that specially constructed machine learning models trained for a specific jet classification task can improve the accuracy, precision, or speed of all other jet physics tasks. This is demonstrated by training on a particular multiclass generation and classification task and then using the learned representation for different generation and classification tasks, for datasets with a different (full) detector simulation, for jets from a different collision system ($pp$ versus $ep$), for generative models, for likelihood ratio estimation, and for anomaly detection. We consider our omnilearn approach thus as a jet-physics foundation model. It is made publicly available for use in any area where state-of-the-art precision is required for analyses involving jets and their substructure.
Mikuni, Vinicius and Nachman, Benjamin. "Method to simultaneously facilitate all jet physics tasks." Physical Review. D., vol. 111, no. 5, Mar. 2025. https://doi.org/10.1103/physrevd.111.054015
Mikuni, Vinicius, & Nachman, Benjamin (2025). Method to simultaneously facilitate all jet physics tasks. Physical Review. D., 111(5). https://doi.org/10.1103/physrevd.111.054015
@article{osti_2531018,
author = {Mikuni, Vinicius and Nachman, Benjamin},
title = {Method to simultaneously facilitate all jet physics tasks},
annote = {Machine learning has become an essential tool in jet physics. Due to their complex, high-dimensional nature, jets can be explored holistically by neural networks in ways that are not possible manually. However, innovations in all areas of jet physics are proceeding in parallel. We show that specially constructed machine learning models trained for a specific jet classification task can improve the accuracy, precision, or speed of all other jet physics tasks. This is demonstrated by training on a particular multiclass generation and classification task and then using the learned representation for different generation and classification tasks, for datasets with a different (full) detector simulation, for jets from a different collision system ($pp$ versus $ep$), for generative models, for likelihood ratio estimation, and for anomaly detection. We consider our omnilearn approach thus as a jet-physics foundation model. It is made publicly available for use in any area where state-of-the-art precision is required for analyses involving jets and their substructure.},
doi = {10.1103/physrevd.111.054015},
url = {https://www.osti.gov/biblio/2531018},
journal = {Physical Review. D.},
issn = {ISSN 2470-0010},
number = {5},
volume = {111},
place = {United States},
publisher = {American Physical Society (APS)},
year = {2025},
month = {03}}
Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 506, Issue 3https://doi.org/10.1016/S0168-9002(03)01368-8
Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 940https://doi.org/10.1016/j.nima.2019.05.097