generalization bound

This paper presents a region-based analysis for the feature concateantion in deep forests.

This paper presents a margin-based generalization bound for deep neural networks.

This is a talk related to the paper “Improving Generalization of Deep Neural Networks by Leveraging Margin Distributions”.

This paper presents a margin-based theory for deep forests.

This is a talk related to the paper “A Refined Margin Distribution Analysis for Forest Representation Learning”.