Sep 23 – 25, 2024
Valencia (Spain)
Europe/Madrid timezone

Exploring End-to-end Differentiable Charged Particle Tracking

Sep 23, 2024, 3:50 PM
20m
Valencia (Spain)

Valencia (Spain)

Computer Science Computer Science

Speaker

Tobias Kortus (University of Kaiserslautern-Landau (RPTU))

Description

Current state-of-the-art in charged particle tracking follows a two-step paradigm where a graph neural network optimizes an intermediate prediction-loss during training and is later combined with a discrete, non-differentiable, optimization step during inference, constructing disconnected track candidates. In this talk, we introduce and assess a novel end-to-end differentiable tracking strategy. We use edge-classifying graph neural networks with differentiable combinatorial components, enabling direct optimization of the task-loss for discrete assignments. We provide further insights into the optimization processes and learned solutions, demonstrating similarities and limitations of two-step and end-to-end optimization. Finally, we demonstrate through a proof of concept that our approach can encode additional constraints or objective functions of downstream tasks, enabling the optimization of tracking solutions that meet specific performance criteria.

Author

Tobias Kortus (University of Kaiserslautern-Landau (RPTU))

Co-authors

Prof. Nicolas R. Gauger (University of Kaiserslautern-Landau (RPTU)) Ralf Keidel (Fachhochschule Worms (DE))

Presentation materials