Improving new physics searches with diffusion models for event observables and jet constituents

no code implementations • 15 Dec 2023 • Debajyoti Sengupta, Matthew Leigh, John Andrew Raine, Samuel Klein, Tobias Golling

We introduce a new technique called Drapes to enhance the sensitivity in searches for new physics at the LHC.

EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion

no code implementations • 29 Sep 2023 • Erik Buhmann, Cedric Ewen, Darius A. Faroughy, Tobias Golling, Gregor Kasieczka, Matthew Leigh, Guillaume Quétant, John Andrew Raine, Debajyoti Sengupta, David Shih

In addition, we introduce \epcfm, the first permutation equivariant continuous normalizing flow (CNF) for particle cloud generation.

PC-Droid: Faster diffusion and improved quality for particle cloud generation

no code implementations • 13 Jul 2023 • Matthew Leigh, Debajyoti Sengupta, John Andrew Raine, Guillaume Quétant, Tobias Golling

Building on the success of PC-JeDi we introduce PC-Droid, a substantially improved diffusion model for the generation of jet particle clouds.

CURTAINs Flows For Flows: Constructing Unobserved Regions with Maximum Likelihood Estimation

no code implementations • 8 May 2023 • Debajyoti Sengupta, Samuel Klein, John Andrew Raine, Tobias Golling

Model independent techniques for constructing background data templates using generative models have shown great promise for use in searches for new physics processes at the LHC.

Anomaly Detection

PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics

1 code implementation • 9 Mar 2023 • Matthew Leigh, Debajyoti Sengupta, Guillaume Quétant, John Andrew Raine, Knut Zoch, Tobias Golling

In this paper, we present a new method to efficiently generate jets in High Energy Physics called PC-JeDi.

Vocal Bursts Intensity Prediction