The Mitchell Conference on Collider, Dark Matter, and Neutrino Physics 2022

Session

Machine Learning, Neutrino

25 May 2022, 08:30

Conveners

Machine Learning, Neutrino

• Joel Walker (Sam Houston State University)

39. Exploring Dark Matter Shadows with AI

Konstantin Matchev (University of Florida (US))

25/05/2022, 08:30

Transit spectroscopy is the primary tool for inferring the physical parameters and the atmospheric chemical composition of extrasolar planets. I will discuss some recently proposed AI-inspired techniques for exoplanet parameter retrievals, including dimensional analysis, vector component analysis, exploratory data analysis, feature engineering, dimensionality reduction and manifold learning,...

4. Fast and Faithful Generation of Calorimeter Showers with Deep Generative Models: CaloFlow.

Dr Claudius Krause (Rutgers University)

25/05/2022, 08:53

Simulation of particle interactions with detector material, especially in the calorimeters are very time-consuming and resource intensive. In the upcoming LHC runs, these could provide a bottleneck that severely limits our analysis capabilities.
In recent years, approaches based on deep generative models have provided a fresh alternative to "classical" fast simulation. In this talk, I present...

13. Classifying Anomalies THrough Outer Density Estimation

Anna Hallin

25/05/2022, 09:16

Despite countless searches at the Large Hadron Collider (LHC), new physics remains elusive. The majority of these searches are highly model specific, requiring both background and signal simulation. In recent years, many anomaly detection methods have been proposed that use machine learning to enhance resonance searches without specifying a particular signal hypothesis. In this talk, I will...

8. Double Higgs Production at the HL-LHC

K.C. Kong

25/05/2022, 09:39

The Higgs potential is vital to understand the electroweak symmetry breaking mechanism, and probing the Higgs self-interaction is arguably one of the most important physics targets at current and upcoming collider experiments. In particular, the triple Higgs coupling may be accessible at the HL-LHC by combining results in multiple channels, which motivates to study all possible decay modes for...

28. $e4\nu$ & $\mu 4 \nu$: Brightening the Future of Neutrino Oscillation Measurements

Joshua Barrow

25/05/2022, 10:02

Sensitivities of future large underground neutrino oscillation experiments are critically dependent upon precisely understanding the initial energy of an incoming neutrino via cross section models and event generator predictions which summarize prospective final states. Extracting the true initial energy of the neutrino is thus model dependent, requiring a deep understanding of the biases...

35. Machine learning the Higgs-top CP Measurement

Rahool Kumar Barman (Oklahoma State University)

We explore the direct Higgs-top CP structure via the $pp \to t\bar{t}h$ channel with machine learning techniques, considering the clean $h \to \gamma\gamma$ final state at the high luminosity LHC~(HL-LHC). We show that a combination of a comprehensive set of observables, that includes the $t\bar{t}$ spin-correlations, with mass minimization strategies to reconstruct the $t\bar{t}$ rest frame...