Machine Learning Algorithms for $b$-Jet Tagging at the ATLAS Experiment

TL;DR

This paper explores the application of modern deep learning techniques to improve $b$-jet tagging in the ATLAS experiment, comparing their performance to traditional classifiers like boosted decision trees.

Contribution

It introduces the use of deep learning methods for $b$-tagging and evaluates their effectiveness against established algorithms using simulated data.

Findings

Deep learning classifiers outperform traditional methods in $b$-tagging accuracy.

Modern techniques leverage detailed track and vertex information.

Results demonstrate potential for improved physics analyses at CERN.

Abstract

The separation of $b$-quark initiated jets from those coming from lighter quark flavors ($b$-tagging) is a fundamental tool for the ATLAS physics program at the CERN Large Hadron Collider. The most powerful $b$-tagging algorithms combine information from low-level taggers, exploiting reconstructed track and vertex information, into machine learning classifiers. The potential of modern deep learning techniques is explored using simulated events, and compared to that achievable from more traditional classifiers such as boosted decision trees.