ML4Jets2020

Session

Decorrelation and Semi/Unsupervised approaches

16 Jan 2020, 09:00

KC 802 (Kimmel Center for University Life)

Conveners

Decorrelation and Semi/Unsupervised approaches

• Nhan Viet Tran (Fermi National Accelerator Lab. (US))
• Chase Owen Shimmin (Yale University (US))

20. Data ex Machina: Machine Learning with Jets in CMS Open Data

Eric Metodiev (Massachusetts Institute of Technology)

16/01/2020, 09:00

In this talk, I explore unsupervised and supervised machine learning techniques using CMS Open Data. I introduce a metric between jets based on the earth (or energy) mover's distance: the “work” required to rearrange one event into the other. Using this metric, I will probe the metric space of jets using unsupervised methods. Further, training supervised jet classifiers directly on data can...

22. Representation Learning for Collider Events

Jack Collins (SLAC)

16/01/2020, 09:20

Variational Autoencoders (VAEs) can be trained to learn representations of metric spaces. I will show how a VAE trained to minimize the Earth Movers Distance (EMD) between input and reconstructed jets learns to represent jet features associated with hierarchically different energy scales in orthogonal directions of its latent space. I will also illustrate the relationship between the...

55. Tagger-mass decorrelation: experience within CMS

Huilin Qu (Univ. of California Santa Barbara (US))

16/01/2020, 09:40

Jet substructure tagging of highly boosted heavy resonances decaying to quarks has become an important tool for Standard Model (SM) measurements and searches for beyond the SM physics. Background estimation typically rely on at least 3 data sideband regions that can be separated from the signal region with the physics process of interest by a set of two uncorrelated variables. For searches...

43. Disco Fever

Gregor Kasieczka (Hamburg University (DE))

16/01/2020, 10:00

With great classification power comes great responsibility: Now that deep-learning is the de-facto standard for jet classification in high-energy physics, attention needs to be paid to aspects beyond performance. A key issue is the question of decorrelation - how a classifier output can be made independent of other salient variables such as the jet's mass. Achieving reliable decorrelation is...

52. A Normalizing Flow Model for Boosted Jets

Matthew Drnevich (NYU)

16/01/2020, 10:20

In this work, we consider dijet production and present a model for the distribution of three-momenta of particles constituting the two boosted jets. Our method involves starting with a simple probability distribution for the momenta in the rest frame of the jets’ parent. Then, we use the Lorentz transformation to map the rest frame momentum distribution into a model of the boosted momenta...

8. Metrics and Machine Learning Algorithms for Collider Space

Ms Tianji Cai (University of California, Santa Barbara)

16/01/2020, 10:39

When the space of collider events is equipped with a metric, many simple-to-use machine learning algorithms can be applied to perform the task of jet tagging. Here we explore several different generalizations of the Energy Mover’s Distance. The computed distance matrices are fed into both supervised and unsupervised learning models, and their performances in distinguishing various types of...

51. Double DisCo: An Automated ABCD Method

David Shih (Rutgers University)

The ABCD method is one of the most highly utilized background estimation procedure in HEP. The key assumption for the method to work is that there are two discriminative features which are independent. Given one feature, there is a growing literature of methods for creating a second feature (as a neural network) which is independent of the first one. While these techniques were designed for...