Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization.

Xingxuan Zhang Renzhe Xu Han Yu Hao Zou Peng Cui

Published in: CoRR (2023)

Keyphrases

objective function
convex functions
higher order
edge detection
decision trees
learning machines
horn clauses
gradient information
norm minimization
multiscale
support vector