A Refined Margin Distribution Analysis for Forest Representation Learning
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)(2019)
摘要
In this paper, we formulate the forest representation learning approach named casForest as an additive model, and show that the generalization error can be bounded by O (ln m/m), when the margin ratio related to the margin standard deviation against the margin mean is sufficiently small. This inspires us to optimize the ratio. To this end, we design a margin distribution reweighting approach for the deep forest model to attain a small margin ratio. Experiments confirm the relation between the margin distribution and generalization performance. We remark that this study offers a novel understanding of casForest from the perspective of the margin theory and further guides the layer-by-layer forest representation learning.
更多查看译文
关键词
deep forest,additive model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要