Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 220142 - Statistical Answers to Astrophysical Questions: A Vital Chapter in the Chase for New Discoveries
Type: Invited
Date/Time: Sunday, August 8, 2021 : 3:30 PM to 5:20 PM
Sponsor: Section on Statistical Computing
Abstract #316794
Title: Model-Independent Detection of New Physics Signals Using Interpretable Semi-Supervised Classifier Tests
Author(s): Mikael Kuusela* and Purvasha Chakravarti and Larry Wasserman and Jing Lei
Companies: Carnegie Mellon University and Imperial College London and Carnegie Mellon University and Carnegie Mellon University
Keywords: anomaly detection; particle physics; Large Hadron Collider; active subspace; mixture model; two-sample testing
Abstract:

A central goal in high energy physics is to detect new physics signals among high-dimensional particle collision data. To do this, one determines whether there is any statistically significant difference between the distribution of Standard Model background samples and the distribution of the experimental observations, which are a mixture of the background and a potential new signal. Traditionally, one also assumes access to a sample from the hypothesized signal distribution leading to a supervised testing problem. Here we instead investigate a model-independent method that uses a semi-supervised classifier test to detect the signal. We also propose a method for estimating the signal strength parameter and use active subspace methods to interpret the fitted classifier in order to understand the properties of the signal. We investigate the performance of these methods on a dataset related to the search for the Higgs boson at the Large Hadron Collider at CERN. We demonstrate that the semi-supervised tests have power comparable to the classical methods for a well-specified signal, but much higher power for an unexpected signal which might be entirely missed by the supervised tests.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program