MACK: Mismodeling Addressed with Contrastive Knowledge

TL;DR

This paper introduces a contrastive learning approach that reduces the impact of mismodeling in machine learning applications for high energy physics, improving robustness without needing detailed mismatch knowledge.

Contribution

The paper proposes a generic contrastive learning methodology that mitigates mismodeling effects in physics ML models without prior mismatch information.

Findings

Effective in jet-tagging at the Large Hadron Collider

Applicable to various tasks beyond high energy physics

Significantly improves model robustness against mismodeling

Abstract

The use of machine learning methods in high energy physics typically relies on large volumes of precise simulation for training. As machine learning models become more complex they can become increasingly sensitive to differences between this simulation and the real data collected by experiments. We present a generic methodology based on contrastive learning which is able to greatly mitigate this negative effect. Crucially, the method does not require prior knowledge of the specifics of the mismodeling. While we demonstrate the efficacy of this technique using the task of jet-tagging at the Large Hadron Collider, it is applicable to a wide array of different tasks both in and out of the field of high energy physics.