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.
Extragradient preference opti- mization (EGPO): Beyond last-iterate convergence for nash learn- ing from human feedback,
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.