We upgraded Indico to version 3.0. The new search is now available as well.
10-15 March 2019
Steinmatte conference center
Europe/Zurich timezone

Direct optimisation of the discovery significance when training neural networks to search for new physics in particle colliders

Not scheduled
20m
Steinmatte conference center

Steinmatte conference center

Hotel Allalin, Saas Fee, Switzerland https://allalin.ch/conference/
Poster Track 2: Data Analysis - Algorithms and Tools Poster Session

Speaker

Dirk Krücker (Deutsches Elektronen-Synchrotron (DE))

Description

We introduce two new loss functions designed to directly optimise the statistical significance of the expected number of signal events when training neural networks to classify events as signal or background in the scenario of a search for new physics at a particle collider. The loss functions are designed to directly maximise commonly used estimates of the statistical significance, s/√(s+b), and the Asimov estimate, Z_A. We consider their use in a toy SUSY search with 30 fb^(−1) of 14 TeV data collected at the LHC. In the case that the search for the SUSY model is dominated by systematic uncertainties, it is found that the loss function based on Z_A can outperform the binary cross entropy in defining an optimal search region.

Primary authors

Dr Adam Christopher Elwood (Deutsches Elektronen-Synchrotron (DE)) Dirk Krücker (Deutsches Elektronen-Synchrotron (DE))

Presentation materials

Peer reviewing

Paper