TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhysCore.8.1.034
TI  - Scaling laws in jet classification
PY  - 2025/03/28
UR  - https://scipost.org/SciPostPhysCore.8.1.034
JF  - SciPost Physics Core
JA  - SciPost Phys. Core
VL  - 8
IS  - 1
SP  - 034
A1  - Batson, Joshua
AU  - Kahn, Yonatan Frederick
AB  - We demonstrate the emergence of scaling laws in the benchmark top versus QCD jet classification problem in collider physics. Six distinct physically-motivated classifiers exhibit power-law scaling of the binary cross-entropy test loss as a function of training set size, with distinct power law indices. This result highlights the importance of comparing classifiers as a function of dataset size rather than for a fixed training set, as the optimal classifier may change considerably as the dataset is scaled up. We speculate on the interpretation of our results in terms of previous models of scaling laws observed in natural language and image datasets.
ER  -

@Article{10.21468/SciPostPhysCore.8.1.034,
	title={{Scaling laws in jet classification}},
	author={Joshua Batson and Yonatan Kahn},
	journal={SciPost Phys. Core},
	volume={8},
	pages={034},
	year={2025},
	publisher={SciPost},
	doi={10.21468/SciPostPhysCore.8.1.034},
	url={https://scipost.org/10.21468/SciPostPhysCore.8.1.034},
}