Estimation and Inference with Trees and Forests in High Dimensions

Abstract

We analyze the finite sample mean squared error (MSE) performance of regression trees and forests in the high dimensional regime with binary features, under a sparsity constraint. We prove that if only $r$ of the $d$ features are relevant for the mean outcome function, then shallow trees built greedily via the CART empirical MSE criterion achieve MSE rates that depend only logarithmically on the ambient dimension $d$. We prove upper bounds, whose exact dependence on the number relevant variables $r$ depends on the correlation among the features and on the degree of relevance. For strongly relevant features, we also show that fully grown honest forests achieve fast MSE rates and their predictions are also asymptotically normal, enabling asymptotically valid inference that adapts to the sparsity of the regression function.

arXiv commentAccepted for presentation at the Conference on Learning Theory (COLT) 2020

References in corpus (7)

• Analysis of a Random Forests Model
• Consistency of random forests
• Narrowing the Gap: Random Forests In Theory and In Practice
• Quantifying Uncertainty in Random Forests via Confidence Intervals and Hypothesis Tests
• Adaptive Concentration of Regression Trees, with Application to Random Forests
• Analysis of purely random forests bias
• Orthogonal Random Forest for Causal Inference

Cited by in corpus (1)

• Double Machine Learning based Program Evaluation under Unconfoundedness