Infinite centered random forests satisfy a central limit theorem with explicit variance, and an importance-sampling debiased version has asymptotically smaller variance for imbalanced classification.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Asymptotic Normality of Infinite Centered Random Forests -Application to Imbalanced Classification
Infinite centered random forests satisfy a central limit theorem with explicit variance, and an importance-sampling debiased version has asymptotically smaller variance for imbalanced classification.