Tree boosting for learning EFT parameters

TL;DR

This paper introduces the Boosted Information Tree algorithm, a novel tree boosting method that leverages Fisher information and likelihood ratios to improve parameter estimation in effective field theory analyses.

Contribution

The paper develops a new boosting algorithm that approximates the score function for EFT parameters using Fisher information, enhancing parameter inference accuracy.

Findings

The algorithm effectively estimates EFT parameters from simulated data.

It utilizes per-event likelihood ratio information for training.

The method provides a sufficient statistic near the reference point.

Abstract

We present a new tree boosting algorithm designed for the measurement of parameters in the context of effective field theory (EFT). To construct the algorithm, we interpret the optimized loss function of a traditional decision tree as the maximal Fisher information in Poisson counting experiments. We promote the interpretation to general EFT predictions and develop a suitable boosting method. The resulting ``Boosted Information Tree'' algorithm approximates the score, the derivative of the log-likelihood function with respect to the parameter. It thus provides a sufficient statistic in the vicinity of a reference point in parameter space where the estimator is trained. The training exploits per-event information of likelihood ratios for different theory parameter values available in the simulated EFT data sets.