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

Xingxuan Zhang Renzhe Xu Han Yu Hao Zou Peng Cui

Published in: CVPR (2023)

Keyphrases

objective function
first order logic
convex functions
higher order
relational learning
norm minimization
term rewriting
edge detection
inductive logic programming
modal logic
efficient optimization
quantifier elimination
linear temporal logic
stochastic dominance