Title: JUNIPR: a framework for unsupervised machine learning in particle physics

Abstract

In applications of machine learning to particle physics, a persistent challenge is how to go beyond discrimination to learn about the underlying physics. To this end, a powerful tool would be a framework for unsupervised learning, where the machine learns the intricate high-dimensional contours of the data upon which it is trained, without reference to pre-established labels. In order to approach such a complex task, an unsupervised network must be structured intelligently, based on a qualitative understanding of the data. In this paper, we scaffold the neural network’s architecture around a leading-order model of the physics underlying the data. In addition to making unsupervised learning tractable, this design actually alleviates existing tensions between performance and interpretability. We call the framework JUNIPR: “Jets from UNsupervised Interpretable PRobabilistic models”. In this approach, the set of particle momenta composing a jet are clustered into a binary tree that the neural network examines sequentially. Training is unsupervised and unrestricted: the network could decide that the data bears little correspondence to the chosen tree structure. However, when there is a correspondence, the network’s output along the tree has a direct physical interpretation. JUNIPR models can perform discrimination tasks, through the statistically optimal likelihood-ratio test, andmore » they permit visualizations of discrimination power at each branching in a jet’s tree. Additionally, JUNIPR models provide a probability distribution from which events can be drawn, providing a data-driven Monte Carlo generator. As a third application, JUNIPR models can reweight events from one (e.g. simulated) data set to agree with distributions from another (e.g. experimental) data set.« less

Authors:

Andreassen, Anders ;

• Search DOE PAGES for author "Andreassen, Anders"
• Search DOE PAGES for ORCID "0000-0003-3504-3919"

Feige, Ilya; Frye, Christopher; Schwartz, Matthew D.

Publication Date:

Fri Feb 01 00:00:00 EST 2019

Research Org.:

Harvard Univ., Cambridge, MA (United States)

Sponsoring Org.:

USDOE Office of Science (SC)

OSTI Identifier:

1619354

Alternate Identifier(s):

OSTI ID: 1612013

Grant/Contract Number:  

SC0013607

Resource Type:

Published Article

Journal Name:

European Physical Journal. C, Particles and Fields

Additional Journal Information:

Journal Name: European Physical Journal. C, Particles and Fields Journal Volume: 79 Journal Issue: 2; Journal ID: ISSN 1434-6044

Publisher:

Springer

Country of Publication:

Germany

Language:

English

Subject:

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; Physics