Hessian-based Analysis of Large Batch Training and Robustness to Adversaries

Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney

Neural Information Processing Systems 

Extensive experiments on multiple networks show that saddle-points are not the cause for generalization gap of large batch size training, and the results consistently show that large batch converges to points with noticeably higher Hessian spectrum.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found