Interpretable Model-Independent Detection of New Physics Signals

Add to your list(s) Download to your calendar using vCal

• Purvasha Chakravarti (Imperial College London)
• Friday 25 February 2022, 14:00-15:00
• MR12, Centre for Mathematical Sciences.

If you have a question about this talk, please contact Qingyuan Zhao.

A central goal in experimental high energy physics is to detect new physics signals that are not explained by known physics. In this talk I will present our algorithm that we use to search for new signals that appear as deviations from known Standard Model physics in high-dimensional particle physics data. To do this, we determine 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. We do this without making any model assumptions on the signal that we are searching for. We use a classifier and construct three test statistics using the classifier: an estimated likelihood ratio test (LRT) statistic, a test based on the area under the ROC curve (AUC), and a test based on the misclassification error (MCE), to detect the presence of the signal in the experimental data. Additionally, I will present our methods for estimating the signal strength parameter and interpreting the high-dimensional classifier in order to understand the properties of the detected signal. I will also present the results on a data set related to the search for the Higgs boson at the Large Hadron Collider at CERN .

This talk is part of the Statistics series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• MR12, Centre for Mathematical Sciences
• Machine Learning
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Statistics
• Statistics Group
• bld31
• custom
• rp587

Note that ex-directory lists are not shown.