A new conformal prediction paper from Brazil 🇧🇷 'Regression Trees for Fast and Adaptive Prediction Intervals' 🔥🔥🔥🔥🔥🚀🚀🚀🚀🚀 'Predictive models make mistakes. Hence, there is a need to quantify the un- certainty associated with their predictions. Conformal inference has emerged as a powerful tool to create statistically valid prediction regions around point predictions, but its naive application to regression problems yields non-adaptive regions. New conformal scores, often relying upon quantile regressors or conditional density estimators, aim to address this limitation. Although they are useful for creating prediction bands, these scores are de- tached from the original goal of quantifying the uncertainty around an ar- bitrary predictive model. This paper presents a new, model-agnostic family of methods to calibrate prediction intervals for regression problems with lo- cal coverage guarantees. Our approach is based on pursuing the coarsest partition of the feature space that approximates conditional coverage. We create this partition by training regression trees and Random Forests on conformity scores. Our proposal is versatile, as it applies to various con- formity scores and prediction settings and demonstrates superior scalability and performance compared to established baselines in simulated and real- world datasets. We provide a Python package locart that implements our methods using the standard scikit-learn interface.' #conformalprediction

[Rethinking Hypothesis Tests] I usually only advertise my papers after they are accepted for publication. But I like this paper (with @kuben45 @FernandoColug @rflassance @altayals @rbstern) so much that I'll do it now. 1/n