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

TL;DR

This paper presents Drapes, a diffusion model-based technique to improve background estimation in LHC new physics searches, enhancing sensitivity by generating more accurate background templates from side-band data.

Contribution

The paper introduces Drapes, a novel diffusion model approach for background template generation, applicable to high-level features and jet constituents, improving search sensitivity at the LHC.

Findings

State-of-the-art background template generation performance.

Effective application to both high-level features and jet constituents.

Sensitivity improvement with some performance loss at low signal significance.

Abstract

We introduce a new technique called Drapes to enhance the sensitivity in searches for new physics at the LHC. By training diffusion models on side-band data, we show how background templates for the signal region can be generated either directly from noise, or by partially applying the diffusion process to existing data. In the partial diffusion case, data can be drawn from side-band regions, with the inverse diffusion performed for new target conditional values, or from the signal region, preserving the distribution over the conditional property that defines the signal region. We apply this technique to the hunt for resonances using the LHCO di-jet dataset, and achieve state-of-the-art performance for background template generation using high level input features. We also show how Drapes can be applied to low level inputs with jet constituents, reducing the model dependence on the choice of input observables. Using jet constituents we can further improve sensitivity to the signal process, but observe a loss in performance where the signal significance before applying any selection is below 4$\sigma$.