On the Importance of Gradient Norm in PAC-Bayesian Bounds.

Itai Gat Yossi Adi Alexander G. Schwing Tamir Hazan

Published in: CoRR (2022)

Keyphrases

pac bayesian
distribution free
generalization bounds
data dependent
error bounds
rademacher complexity
objective function
normal distribution
decision trees
vc dimension
statistical learning theory
large deviations