Linearized Optimal Transport for Collider Events

TL;DR

This paper presents a computationally efficient Linearized Optimal Transport framework for measuring distances between collider events, enabling improved machine learning applications and visualization in high-energy physics.

Contribution

It introduces a novel LOT-based method that reduces computational costs and provides a Euclidean embedding for collider event analysis, enhancing previous energy mover's distance approaches.

Findings

Reduced computational cost compared to previous methods

Effective jet tagging demonstrated with machine learning

Provides a Euclidean embedding for collider events

Abstract

We introduce an efficient framework for computing the distance between collider events using the tools of Linearized Optimal Transport (LOT). This preserves many of the advantages of the recently-introduced Energy Mover's Distance, which quantifies the "work" required to rearrange one event into another, while significantly reducing the computational cost. It also furnishes a Euclidean embedding amenable to simple machine learning algorithms and visualization techniques, which we demonstrate in a variety of jet tagging examples. The LOT approximation lowers the threshold for diverse applications of the theory of optimal transport to collider physics.