Linearized Optimal Transport for Collider Events
This work addresses the need for faster and more accessible optimal transport methods in collider physics, though it is incremental as it builds on existing approaches.
The paper tackles the problem of efficiently computing distances between collider events in physics by introducing a Linearized Optimal Transport framework, which reduces computational cost compared to the Energy Mover's Distance and enables Euclidean embeddings for machine learning and visualization in jet tagging examples.
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.