Towards Universal Unfolding using Denoising Diffusion

Large Hadron Collider Physics Conference (LHCP), pp. 234

Abstract

Correcting for detector effects in experimental data, particularly through unfolding, is critical for enabling precision measurements in high-energy physics. However, traditional unfolding methods face challenges in scalability, flexibility, and dependence on simulations. We introduce a novel approach to multidimensional object-wise unfolding using conditional Denoising Diffusion Probabilistic Models (cDDPM). Our method utilizes the cDDPM for a non-iterative, flexible posterior sampling approach, incorporating distribution moments as conditioning information, which exhibits a strong inductive bias that allows it to generalize to unseen physics processes without explicitly assuming the underlying distribution. Our results highlight the potential of this method as a step towards a "universal" unfolding tool that reduces dependence on truth-level assumptions, while enabling the unfolding of a wide range of measured distributions with enhanced flexibility and accuracy.

Authors 6

1. Camila Pazos

   The NSF AI Institute for Artificial Intelligence and Fundamental Interactions

   Affiliation as printed

   The NSF AI Institute for Artificial Intelligence and Fundamental

2. Shuchin Aeron

   Tufts University

   Affiliation as printed

   Department of Electrical and Computer Engineering , Tufts University , Medford , Massachusetts

3. P. H. Beauchemin

   Tufts University

   Affiliation as printed

   Department of Physics and Astronomy , Tufts University , Medford , Massachusetts

4. V. Croft Aachen Leiden Institute for Advanced Computer Science LIACS

   Leiden University

   Affiliation as printed

   Leiden Institute for Advanced Computer Science LIACS , Leiden University , The Netherlands 𝑑

5. M. Klassen

   The NSF AI Institute for Artificial Intelligence and Fundamental Interactions

   Affiliation as printed

   The NSF AI Institute for Artificial Intelligence and Fundamental

6. T. Wongjirad