Binning high-dimensional classifier output for HEP analyses through a clustering algorithm

The usage of Deep Neural Networks (DNNs) as multi-classifiers is widespread in modern HEP analyses. In standard categorisation methods, the high-dimensional output of the DNN is often reduced to a one-dimensional distribution by exclusively passing the information about the highest class score to th...

Full description

Saved in:
Bibliographic Details
Published in:EPJ Web of conferences 2024, Vol.295, p.6005
Main Authors: Diekmann, Svenja, Eich, Niclas, Erdmann, Martin
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Classification
Classifiers
Cluster analysis
Clustering
Statistical inference
Vector quantization
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The usage of Deep Neural Networks (DNNs) as multi-classifiers is widespread in modern HEP analyses. In standard categorisation methods, the high-dimensional output of the DNN is often reduced to a one-dimensional distribution by exclusively passing the information about the highest class score to the statistical inference method. Correlations to other classes are hereby omitted. Moreover, in common statistical inference tools, the classification values need to be binned, which relies on the researcher’s expertise and is often nontrivial. To overcome the challenge of binning multiple dimensions and preserving the correlations of the event-related classification information, we perform K-means clustering on the high-dimensional DNN output to create bins without marginalising any axes. We evaluate our method in the context of a simulated cross section measurement at the CMS experiment, showing an increased expected sensitivity over the standard binning approach.
ISSN:2100-014X
2101-6275
2100-014X
DOI:10.1051/epjconf/202429506005