Artificial Intelligence and the Uncertainty challenge in Fundamental Physics

Session

Unfolding (de-biasing)

30 nov. 2023, 09:00

Présidents de session

Unfolding (de-biasing)

• Thomas Vuillaume (LAPP, Univ. Savoie Mont-Blanc, CNRS)
• Olaf Behnke (DESY)

38. Unfolding in High Energy Physics

Vincent Alexander Croft (LIACS)

30/11/2023 09:00

In high-energy physics, unfolding is a critical statistical process for interpreting experimental data that is complicated by the intrinsic ill-posedness of the problem. This complexity arises from the need to provide heuristics for statistical estimates that disentangle true physical phenomena from observational distortions. We present a typical roadmap for why, when, and how unfolding is...

2. An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative training

Mathias Josef Backes (Kirchhoff Institut für Physik)

30/11/2023 09:45

Unfolding

The unfolding of detector effects is crucial for the comparison of data to theory predictions. While traditional methods are limited to representing the data in a low number of dimensions, machine learning has enabled new unfolding techniques while retaining the full dimensionality. Generative networks like invertible neural networks (INN) enable a probabilistic unfolding, which maps...

3. Can contrastive learning de-bias my model?

Radi Radev (CERN)

30/11/2023 10:15

Unfolding

Deep learning models have become ubiquitous in high-energy physics and have been successfully applied to a wide variety of tasks. Models for reconstruction are usually trained from scratch on a nominal set of simulation parameters, not taking into account variations of detector systematic uncertainties.

Following advances in contrastive learning, we present a method of pre-training a...

39. Uncertainty Quantification and Anomaly Detection with Evidential Deep Learning

Mark Neubauer (University of Illinois at Urbana-Champaign)

30/11/2023 11:15

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 will discuss its connection...