Poster
A Refined Margin Distribution Analysis for Forest Representation Learning
Shen-Huan Lyu · Liang Yang · Zhi-Hua Zhou
East Exhibition Hall B, C #6
Keywords: [ Algorithms ] [ Boosting and Ensemble Methods ] [ Algorithms -> Classification; Algorithms ] [ Large Margin Methods ]
[
Abstract
]
Abstract:
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 $\mathcal{O}(\ln m/m)$, 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.
Live content is unavailable. Log in and register to view live content