Related papers: Studies of Boosted Decision Trees for MiniBooNE Pa…
MiniBooNE is a neutrino oscillation experiment now running at Fermilab. The experiment will search for muon neutrino to electron neutrino oscillations in order to make a conclusive statement about the yet-unconfirmed evidence for…
We present an application of a particular machine-learning method (Boosted Decision Trees, BDTs using AdaBoost) to separate stars and galaxies in photometric images using their catalog characteristics. BDTs are a well established machine…
Decision trees are a widely used method for classification, both by themselves and as the building blocks of multiple different ensemble learning methods. The Max-Cut decision tree involves novel modifications to a standard, baseline model…
Gradient tree boosting is a prediction algorithm that sequentially produces a model in the form of linear combinations of decision trees, by solving an infinite-dimensional optimization problem. We combine gradient boosting and Nesterov's…
This paper investigates the integration of gradient boosted decision trees and varying coefficient models. We introduce the tree boosted varying coefficient framework which justifies the implementation of decision tree boosting as the…
Neutrino oscillations provide an unique opportunity to probe physics beyond the Standard Model. Fermilab is constructing two new neutrino beams to provide a decicive test of two of the recent positive indications for neutrino oscillations:…
Statistical learning methods have been growing in popularity in recent years. Many of these procedures have parameters that must be tuned for models to perform well. Research has been extensive in neural networks, but not for many other…
This paper illustrates a generic method for multi-dimensional reweighting of $O(1)$ GeV neutrino interaction Monte Carlo samples. The reweighting is based on a Boosted Decision Tree algorithm trained on high-dimensional space in detector…
Gradient Boosting Decision Tree (GBDT) are popular machine learning algorithms with implementations such as LightGBM and in popular machine learning toolkits like Scikit-Learn. Many implementations can only produce trees in an offline…
We present a measurement of electron neutrino interactions from the Fermilab Booster Neutrino Beam using the MicroBooNE liquid argon time projection chamber to address the nature of the excess of low energy interactions observed by the…
We train several neural networks and boosted decision trees to discriminate fully-hadronic boosted di-$\tau$ topologies against background QCD jets, using calorimeter and tracking information. Boosted di-$\tau$ topologies consisting of a…
Machine learning algorithms are now being extensively used in our daily lives, spanning across diverse industries as well as academia. In the field of high energy physics (HEP), the most common and challenging task is separating a rare…
Gradient boosted decision trees have achieved remarkable success in several domains, particularly those that work with static tabular data. However, the application of gradient boosted models to signal processing is underexplored. In this…
The MiniBooNE neutrino oscillation search experiment at Fermilab has recently updated results from a search for $\bar\nu_\mu \rightarrow \bar\nu_e$ oscillations, using a data sample corresponding to $8.58 \times 10^{20}$ protons on target…
Boosted decision trees typically yield good accuracy, precision, and ROC area. However, because the outputs from boosting are not well calibrated posterior probabilities, boosting yields poor squared error and cross-entropy. We empirically…
We compare the observed charged particle multiplicity distributions in the MicroBooNE liquid argon time projection chamber from neutrino interactions in a restricted final state phase space to predictions of this distribution from several…
This paper evaluates the performance of boosted decision trees for tagging b-jets. It is shown, using a Monte Carlo simulation of $WH \to l\nu q\bar{q}$ events that boosted decision trees outperform feed-forward neural networks. The results…
The upcoming long baseline neutrino experiments aim to enhance proton beam power to multi-MW scale and utilize large-scale detectors to address the challenge of limited event statistics. The DUNE experiment at LBNF will test the three…
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on…
The MiniBooNE experiment is a $\nu_\mu\to\nu_e$ and $\bar\nu_\mu\to\bar\nu_e$ appearance neutrino oscillation experiment at Fermilab. The neutrino mode oscillation analysis shows an excess of $\nu_e$ candidate events in the low-energy…