random-forest-adaptive-neighborhood-kernel

IN premise — entries/2026/06/21/wiki-Random_forest-chunk-2.md

Created 2026-06-21T09:55:51+00:00

Random forests can be interpreted as adaptive kernel smoothers: the prediction is a weighted average over training points, where the weight function (defined by shared leaf membership across trees) adapts to local feature relevance, unlike k-NN's fixed-shape neighborhoods.