ML4Jets2024

Session

Uncertainties & Interpretability

6 Nov 2024, 10:50

LPNHE, Paris, France

Conveners

Uncertainties & Interpretability

• Martin Klassen (Tufts University (US))

Uncertainties & Interpretability

• Manuel Szewc

11. Frequentist Uncertainties on Density Ratios with Ensembles

Sean Benevedes (Massachusetts Institute of Technology)

06/11/2024, 10:50

We propose a novel framework to obtain asymptotic frequentist uncertainties on machine learned classifier outputs by using model ensembles. With the well-known likelihood trick, this framework can then be applied to the task of density ratio estimation to obtain statistically rigorous frequentist uncertainties on estimated likelihood ratios. As a toy example, we demonstrate that the framework...

41. Machine Learning the Top Mass

Katherine Fraser (Harvard University)

06/11/2024, 11:10

Energy correlators have recently shown potential to improve the precision on the top mass precision measurement. However, existing measurement strategies still only use part of the information in the EEEC distribution and rely on arbitrary shape choices. In this talk, we explore the ability of Machine Learning to effectively optimize shape choice and reduce error on the top mass. Specifically,...

39. Calibrating ATLAS calorimeter signals using an uncertainty-aware precision network

Mr Lorenz Vogel (Heidelberg University)

06/11/2024, 11:30

ATLAS explores modern neural networks for a multi-dimensional calibration of its calorimeter signal defined by clusters of topologically connected cells (topo-clusters). The Bayesian neural network (BNN) approach yields a continuous and smooth calibration function, including uncertainties on the calibrated energy per topo-cluster. In this talk the performance of this BNN-derived calibration is...

101. Uncertainty Quantification and Anomaly Detection with Evidential Deep Learning

Mark Neubauer (Univ. Illinois at Urbana Champaign (US))

06/11/2024, 11:50

Evidential Deep Learning (EDL) is an uncertainty-aware deep learning approach designed to provide confidence (or epistemic uncertainty) about test data. It treats learning as an evidence acquisition process where more evidence is interpreted as increased predictive confidence. This talk will provide a brief overview of EDL for uncertainty quantification (UQ) and its application to jet tagging...

91. The good, the bad, and the Bayesian?

Nina Elmer

07/11/2024, 09:00

Estimating uncertainties is a fundamental aspect in every physics problem, no measurements or calculations comes without uncertainties. Hence it is crucial to consider the effect of training a neural network to problems in physics. I will present our work on amplitude regression, using loop amplitudes from LHC processes, as an example to examine the impact of different uncertainties on the...

53. Calibrating Bayesian Generative Machine Learning for Bayesiamplification

Sebastian Guido Bieringer (Hamburg University)

07/11/2024, 09:20

Generative models are on a fast track to becoming a mainstay in particle physics simulation chains, seeing active work towards adoption by nearly every large experiment and collaboration. However, the question of estimating the uncertainties and statistical expressiveness of samples produced by generative ML models is still far from settled.

Recently, combinations of generative and...

48. KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics example

Florian Alexander Mausolf (Rheinisch Westfaelische Tech. Hoch. (DE))

07/11/2024, 09:40

Recently, Kolmogorov-Arnold Networks (KANs) have been proposed as an alternative to multilayer perceptrons, suggesting advantages in performance and interpretability. In this talk, we present the first application of KANs in high-energy physics, focusing on a typical binary classification task involving high-level features.
We study KANs with different depths and widths and include a...

107. ParticleNet: Calibration of the jet energy scale using pT regression with partial Run3 data collected by the CMS experiment

Matteo Malucchi (ETH Zurich (CH))

07/11/2024, 10:00

We are presenting the first calibration of the jet pT regression (CMS-DP-2024-064), achieving an expected improvement in jet resolution of up to 17%, and the latest performance results for flavor identification and jet energy resolution estimation using ParticleNet. The pT regression, which focuses on correcting the reconstructed jet pT to the truth-level jet pT, is divided into two...