MinimaxSplit trees and forests minimize maximum child impurity for splits, with oracle inequalities claiming faster excess risk convergence than CART under non-atomicity conditions, plus empirical gains on EEG regression and image denoising.
On the pointwise behavior of recursive parti- tioning and its implications for heterogeneous causal effect estimation.arXiv preprint arXiv:2211.10805
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stabilizing the Splits through Minimax Decision Trees
MinimaxSplit trees and forests minimize maximum child impurity for splits, with oracle inequalities claiming faster excess risk convergence than CART under non-atomicity conditions, plus empirical gains on EEG regression and image denoising.