Adversarial training reduces loss sharpness and improves cross-Monte-Carlo generalization for Higgs-jet classifiers, with projected gradient descent giving the largest gains.
VI C, where feature- space attack methods generalize better from Herwig to Pythia than from Pythia to Herwig, whereas weight-space attacks show the opposite trend
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-ph 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing generalization in high energy physics using white-box adversarial attacks
Adversarial training reduces loss sharpness and improves cross-Monte-Carlo generalization for Higgs-jet classifiers, with projected gradient descent giving the largest gains.