19–23 May 2025
CERN
Europe/Zurich timezone

Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation

21 May 2025, 15:20
20m
222/R-001 (CERN)

222/R-001

CERN

200
Show room on map
Contributed talk 2 ML for analysis: Event classification, statistical analysis and inference, anomaly detection Contributed Talks

Speaker

Ibrahim Elsharkawy (University of Illinois Urbana-Champaign)

Description

Abstract The fields of High-Energy physics (HEP) and machine learning (ML) converge on the challenge of uncertainty-aware parameter estimation in the presence of data distribution distortions, described in their respective languages --- systematic uncertainties and domain shifts. We present a novel approach based on Contrastive Normalizing Flows (CNFs), which achieved top performance on the HiggsML Uncertainty Challenge. Building on the insight that a binary classifier can approximate the model parameter likelihood ratio, $\frac{P(x_i|\theta_1,)}{P(x_i|\theta_2,)}$ we address the practical limitations of expressivity and the high cost of simulating high-dimensional parameter grids—by embedding data and parameters in a learned CNF mapping. This mapping models a unique and tunable contrastive distribution that enables robust classification under shifted data distributions. Through a combination of theoretical analysis and empirical evaluations, we show that CNFs, when coupled with a classifier and proper statistics, provide principled parameter estimation and uncertainty quantification through robust classification.

Context This is the method paper for a top-performing solution to the Higgs Uncertainty Challenge (https://arxiv.org/abs/2410.02867). This will also be presented at the Fair Universe HiggsML Uncertainty CERN workshop.

Would you like to be considered for an oral presentation? Yes

Author

Ibrahim Elsharkawy (University of Illinois Urbana-Champaign)

Co-author

Yonatan Kahn (University of Toronto)

Presentation materials