E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once

by   Benjamin Nachman, et al.

There have been a number of recent proposals to enhance the performance of machine learning strategies for collider physics by combining many distinct events into a single ensemble feature. To evaluate the efficacy of these proposals, we study the connection between single-event classifiers and multi-event classifiers under the assumption that collider events are independent and identically distributed (IID). We show how one can build optimal multi-event classifiers from single-event classifiers, and we also show how to construct multi-event classifiers such that they produce optimal single-event classifiers. This is illustrated for a Gaussian example as well as for classification tasks relevant for searches and measurements at the Large Hadron Collider. We extend our discussion to regression tasks by showing how they can be phrased in terms of parametrized classifiers. Empirically, we find that training a single-event (per-instance) classifier is more effective than training a multi-event (per-ensemble) classifier, as least for the cases we studied, and we relate this fact to properties of the loss function gradient in the two cases. While we did not identify a clear benefit from using multi-event classifiers in the collider context, we speculate on the potential value of these methods in cases involving only approximate independence, as relevant for jet substructure studies.


page 1

page 2

page 3

page 4


hepaccelerate: Fast Analysis of Columnar Collider Data

At HEP experiments, processing terabytes of structured numerical event d...

External Evaluation of Event Extraction Classifiers for Automatic Pathway Curation: An extended study of the mTOR pathway

This paper evaluates the impact of various event extraction systems on a...

Multi-Class Multiple Instance Learning for Predicting Precursors to Aviation Safety Events

In recent years, there has been a rapid growth in the application of mac...

Preserving physically important variables in optimal event selections: A case study in Higgs physics

Analyses of collider data, often assisted by modern Machine Learning met...

Classification of Equation of State in Relativistic Heavy-Ion Collisions Using Deep Learning

Convolutional Neural Nets, which is a powerful method of Deep Learning, ...

Acoustic Event Detection with Classifier Chains

This paper proposes acoustic event detection (AED) with classifier chain...