AI & ML
Assessing model calibration with boosting trees
arXiv stat.TH0 views
arXiv:2606.08084v2 Announce Type: replace Abstract: The main goal in regression modelling consists in approximating the conditional mean of a response given a set of features. A regression function is said to be strongly calibrated if the resulting mean estimates match the true conditional means for almost every set of features. Aiming for strong calibration seems not achievable in practice as one typically deals with finite samples of noisy observations. A weaker notion of calibration is auto-calibration, and it means that the conditional expectation of the response, given a mean estimate, matches this estimate. This notion is important, e.g., in insurance pricing as it ensures no cross-subsidization between different price cohorts. In this paper, we show that boosting trees can be used to test necessary conditions for strong calibration and auto-calibration, respectively. The practical relevance of our approach is supported by a numerical example, in which the proposed tests achieve high empirical power.
Source:https://arxiv.org/abs/2606.08084PreviousOn the Validity of Fisher Randomization Tests under the Weak NullNextNonparametric Regression on Fixed-Cardinality Subsets:Minimax Risk and Random-Design Effects
Related posts

iOS 27 gave AirPods Pro a convenient new setting, here’s how to use it
09to5Mac
![Motorola’s iPhone Duo competitor, Razr Flex, leaks in detailed images [Gallery]](https://9to5google.com/wp-content/uploads/sites/4/2026/11/motorola-razr-flex-leak-sg-1.jpg?quality=82&strip=all&w=1600)
Motorola’s iPhone Duo competitor, Razr Flex, leaks in detailed images [Gallery]
09to5Google

AI features could be turned off with a simple toggle, Canva proves
09to5Google
Manuj Mittal on Why “Most Tokens Aren’t Securities” Leaves Crypto With More Questions Than Answers
0HackerNoon
I Found My Own Website Blocking ChatGPT. Then I Checked 640 Others.
0HackerNoon

Small Language Models, Not Giant LLMs, Should Power the Next Generation of AI Agents
0HackerNoon