Pretraining neural networks on fast simulation yields reusable representations that improve performance on full simulation tasks in LHC environments while cutting required target statistics by a factor of about two.
Narayanan, Gianfranco de Castro, Maxim Goncharov, Christoph Paus, and Matthias Schott
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Transfer Learning Across Fast- and Full-Simulation Domains in High-Energy Physics
Pretraining neural networks on fast simulation yields reusable representations that improve performance on full simulation tasks in LHC environments while cutting required target statistics by a factor of about two.