EISAM adds an extragradient-inspired prediction step to SAM, yielding better generalization and reduced sensitivity to the perturbation radius across image, text, and detection tasks.
An investigation into neural net optimization via hessian eigenvalue density,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning
EISAM adds an extragradient-inspired prediction step to SAM, yielding better generalization and reduced sensitivity to the perturbation radius across image, text, and detection tasks.