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

Itai Gat Yossi Adi Alexander G. Schwing Tamir Hazan

Published in: NeurIPS (2022)

Keyphrases

pac bayesian
distribution free
generalization bounds
data dependent
rademacher complexity
error bounds
generalization ability
learning algorithm
support vector
worst case
large deviations
risk bounds