Neural embedding: learning the embedding of the manifold of physics data
Name
13130_2023_Article_21320.pdf
Size
4.53 MB
Format
Adobe PDF
Checksum (MD5)
0a0fdb2813efe4a06f1ccfc98a2dc2fa
Author(s)
Park, Sang E.
Harris, Philip
Ostdiek, Bryan
Date Issued
July 12, 2023
Publisher
Springer Berlin Heidelberg
Citation
Journal of High Energy Physics. 2023 Jul 12;2023(7):108
Version
Final published version
Abstract
Abstract
In this paper, we present a method of embedding physics data manifolds with metric structure into lower dimensional spaces with simpler metrics, such as Euclidean and Hyperbolic spaces. We then demonstrate that it can be a powerful step in the data analysis pipeline for many applications. Using progressively more realistic simulated collisions at the Large Hadron Collider, we show that this embedding approach learns the underlying latent structure. With the notion of volume in Euclidean spaces, we provide for the first time a viable solution to quantifying the true search capability of model agnostic search algorithms in collider physics (i.e. anomaly detection). Finally, we discuss how the ideas presented in this paper can be employed to solve many practical challenges that require the extraction of physically meaningful representations from information in complex high dimensional datasets.
MIT Department
Massachusetts Institute of Technology. Department of Physics
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/JHEP07(2023)108
