Toward Better Generalization Bounds with Locally Elastic Stability

Zhun Deng
Cited by: 0|Views28

Abstract:

Classical approaches in learning theory are often seen to yield very loose generalization bounds for deep neural networks. Using the example of "stability and generalization" \citep{bousquet2002stability}, however, we demonstrate that generalization bounds can be significantly improved by taking into account refined characteristics of m...More

Code:

Data:

Full Text
Bibtex