A PAC-Bayesian Generalization Bound for Equivariant Networks Arash Behboodi Qualcomm AI Research, Amsterdam

Neural Information Processing Systems 

In this paper, we study how equivariance relates to generalization error utilizing P AC Bayesian analysis for equivariant networks, where the transformation laws of feature spaces are determined by group representations.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found