QCD-Aware Neural Networks for Jet Physics

by Kyle Stuart Cranmer (New York University (US))

Wednesday 24 May 2017, 14:00 → 15:30 Europe/Zurich

4/3-006 - TH Conference Room (CERN)

Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images. In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. In the analogy, four-momenta are like words and the clustering history of sequential recombination jet algorithms is like the parsing of a sentence. Our approach works directly with the four-momenta of a variable-length set of particles, and the jet-based neural network topology varies on an event-by-event basis. Our experiments highlight the flexibility of our method for building task-specific jet embeddings and show that recursive architectures are significantly more accurate and data efficient than previous image-based networks. We extend the analogy from individual jets (sentences) to full events (paragraphs), and show for the first time an event-level classifier operating on all the stable particles produced in an LHC event. I will discuss future directions for this style of hybrid physics-aware machine learning algorithms.

paper: learning to pivot with adversarial neural networks

paper: QCD-aware recursive neural networks

QCD-aware-RNN-CERN.pdf

Recording