Improving new physics searches with diffusion models for event observables and jet constituents
This addresses the challenge of detecting rare signals in high-energy physics experiments, offering a novel method for background estimation that could impact particle physics research.
The paper tackled the problem of enhancing sensitivity in new physics searches at the LHC by introducing Drapes, a technique using diffusion models to generate background templates from side-band data, achieving state-of-the-art performance on the LHCO di-jet dataset and improving sensitivity with jet constituents.
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$σ$.