Mixture-of-theories Training: Can We Find New Physics and Anomalies Better by Mixing Physical Theories?

Abstract

Model-independent search strategies have been increasingly proposed in recent years because on the one hand there has been no clear signal for new physics and on the other hand there is a lack of a highly probable and parameter-free extension of the standard model. For these reasons, there is no simple search target so far. In this work, we try to take a new direction and ask the question: bearing in mind that we have a large number of new physics theories that go beyond the Standard Model and may contain a grain of truth, can we improve our search strategy for unknown signals by using them "in combination"? In particular, we show that a signal hypothesis based on a large, intermingled set of many different theoretical signal models can be a superior approach to find an unknown BSM signal. Applied to a recent data challenge, we show that "mixture-of-theories training" outperforms strategies that optimize signal regions with a single BSM model as well as most unsupervised strategies. Applications of this work include anomaly detection and the definition of signal regions in the search for signals of new physics.

arXiv comment40 pages, 10 figures

References in corpus (34)

• An Introduction to PYTHIA 8.2
• Asymptotic formulae for likelihood-based tests of new physics
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• FeynRules 2.0 - A complete toolbox for tree-level phenomenology
• MadGraph 5 : Going Beyond
• A Supersymmetry Primer
• UFO - The Universal FeynRules Output
• Theories with Gauge-Mediated Supersymmetry Breaking
• SARAH 4: A tool for (not only SUSY) model builders
• Anomaly Detection with Density Estimation
• Classification without labels: Learning from mixed samples in high energy physics
• Searching for New Physics with Deep Autoencoders
• Updated Global SMEFT Fit to Higgs, Diboson and Electroweak Data
• Anomaly Detection for Resonant New Physics with Machine Learning
• Parameterized Machine Learning for High-Energy Physics
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• QCD or What?
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Variational Autoencoders for New Physics Mining at the Large Hadron Collider
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Learning to Classify from Impure Samples with High-Dimensional Data
• Weakly Supervised Classification in High Energy Physics
• The BSM-AI project: SUSY-AI - Generalizing LHC limits on Supersymmetry with Machine Learning
• (Machine) Learning to Do More with Less
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Doubly Charged Higgs Boson Production at Hadron Colliders
• Minimal Dilaton Model
• Model independent reach for W-prime bosons at the LHC
• Constraining the Parameters of High-Dimensional Models with Active Learning
• Discriminating signal from background using neural networks. Application to top-quark search at the Fermilab Tevatron
• Constraints on Mediator Coupled to Heavy Quarks from LHC Data
• Constraints on a Light Leptophobic Mediator from LEP Data

Cited by in corpus (2)

• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Non-resonant Anomaly Detection with Background Extrapolation