Machine Learning for Jet Physics

Session

Learning more about QCD

12 Dec 2017, 09:00

2-100 (Lawrence Berkeley National Laboratory)

Contribution list Timetable

27. Introduction and Overview (15'+5')

Yang-Ting Chien (MIT)

12/12/2017, 09:00

3. Machine learning in the Lund plane (15'+5')

Frederic Dreyer (MIT)

12/12/2017, 09:20

We introduce a novel representation for emission patterns inside a jet, by declustering a Cambridge-Aachen jet and using the primary-emission Lund plane coordinates. We present several possible variations of this method, and show how it can be used to construct either an n by n pixel image or a graph, which can be used as inputs for neural networks. Using W tagging as an example, we show...

2. A complete, linear basis for (machine) learning jet substructure (15'+5')

Mr Eric Metodiev (MIT)

12/12/2017, 09:40

In this talk, I will present Energy Flow Polynomials (EFPs), a novel class of jet substructure observables that form a discrete, linear basis of all infrared- and collinear-safe information in a jet. The EFPs are multiparticle energy correlators with a powerful graph-theoretic interpretation which encompass and generalize the analytic structures present in many existing classes of jet...

1. Linear jet tagging with the energy flow basis (15'+5')

Mr Patrick Komiske (MIT)

12/12/2017, 10:00

In this talk, I will demonstrate the linear power of Energy Flow Polynomials (EFPs) by applying linear classification methods to quark/gluon discrimination, boosted W tagging, and boosted top tagging, achieving performance that compares favorably to other jet representations and modern machine learning approaches. I will briefly describe novel algorithms that make use of the graph-theoretic...

10. Learning the Physics of Jet Evolution with a Recurrent Neural Network Part I (15')

Anders ANDREASSEN (Harvard)

12/12/2017, 10:20

Many early applications of Machine Learning in jet physics are classifiers that use Convolutional Neural Networks trained on jet images. We will present a work-in-progress custom probabilistic model, tailored to learning the physics of jet production in an unsupervised way. Our model is built on a Recurrent Neural Network suited to modeling the approximate sequential splitting of a tree, which...

26. Learning the Physics of Jet Evolution with a Recurrent Neural Network Part II (15'+5')

Frye Chris (Harvard)

12/12/2017, 10:35