Back To The Roots: Tree-Based Algorithms for Weakly Supervised Anomaly Detection

TL;DR

This paper demonstrates that boosted decision trees outperform neural networks in weakly supervised anomaly detection at the LHC, offering faster training, robustness to noise, and improved performance for model-agnostic new physics searches.

Contribution

The paper introduces the use of advanced gradient boosted decision trees in weakly supervised anomaly detection, enhancing robustness and efficiency over neural networks.

Findings

Boosted decision trees outperform neural networks in detection accuracy.

Training and evaluation are significantly faster with decision trees.

Robustness to noisy features improves detection performance.

Abstract

Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (LHC). While these methods have shown remarkable performance on specific signatures such as di-jet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. In this paper, we show that using boosted decision trees as classifiers in weakly supervised anomaly detection gives superior performance compared to deep neural networks. Boosted decision trees are well known for their effectiveness in tabular data analysis. Our results show that they not only offer significantly faster training and evaluation times, but they are also robust to a large number of noisy input features. By using advanced gradient boosted decision trees in combination with ensembling techniques and an extended set of features, we significantly improve the performance of weakly supervised methods for anomaly detection at the LHC. This advance is a crucial step towards a more model-agnostic search for new physics.