Multivariate Gaussian Approximation for Random Forest via Region-based Stabilization

arXiv:2403.09960v1 Announce Type: cross
Abstract: We derive Gaussian approximation bounds for random forest predictions based on a set of training points given by a Poisson process, under fairly mild regularity assumptions on the data generating process. Our approach is based on the key observation that the random forest predictions satisfy a certain geometric property called region-based stabilization. In the process of developing our results for the random forest, we also establish a probabilistic result, which might be of independent interest, …

abstract approximation arxiv assumptions data key math.st multivariate observation predictions process random set stat.ml stat.th the key training type via