Contributor info: Dr Sascha Diefenbacher

Anja Butter, Sascha Diefenbacher, Nathan Huetsch, Vinicius Mikuni, Benjamin Nachman, Sofia Palacios Schweitzer, Tilman Plehn

SciPost Phys. 18, 200 (2025) · published 20 June 2025 | Toggle abstract · pdf

Machine learning enables unbinned, highly-differential cross section measurements. A recent idea uses generative models to morph a starting simulation into the unfolded data. We show how to extend two morphing techniques, Schrödinger Bridges and Direct Diffusion, in order to ensure that the models learn the correct conditional probabilities. This brings distribution mapping (DM) to a similar level of accuracy as the state-of-the-art conditional generative unfolding methods. Numerical results are presented with a standard benchmark dataset of single jet substructure as well as for a new dataset describing a 22-dimensional phase space of $Z+2$-jets.

Nathan Huetsch, Javier Mariño Villadamigo, Alexander Shmakov, Sascha Diefenbacher, Vinicius Mikuni, Theo Heimel, Michael Fenton, Kevin Greif, Benjamin Nachman, Daniel Whiteson, Anja Butter, Tilman Plehn

SciPost Phys. 18, 070 (2025) · published 25 February 2025 | Toggle abstract · pdf

Recent innovations from machine learning allow for data unfolding, without binning and including correlations across many dimensions. We describe a set of known, upgraded, and new methods for ML-based unfolding. The performance of these approaches are evaluated on the same two datasets. We find that all techniques are capable of accurately reproducing the particle-level spectra across complex observables. Given that these approaches are conceptually diverse, they offer an exciting toolkit for a new class of measurements that can probe the Standard Model with an unprecedented level of detail and may enable sensitivity to new phenomena.

Anja Butter, Sascha Diefenbacher, Gregor Kasieczka, Benjamin Nachman, Tilman Plehn, David Shih, Ramon Winterhalder

SciPost Phys. 13, 087 (2022) · published 7 October 2022 | Toggle abstract · pdf

The large data rates at the LHC require an online trigger system to select relevant collisions. Rather than compressing individual events, we propose to compress an entire data set at once. We use a normalizing flow as a deep generative model to learn the probability density of the data online. The events are then represented by the generative neural network and can be inspected offline for anomalies or used for other analysis purposes. We demonstrate our new approach for a toy model and a correlation-enhanced bump hunt.

Anja Butter, Sascha Diefenbacher, Gregor Kasieczka, Benjamin Nachman, Tilman Plehn

SciPost Phys. 10, 139 (2021) · published 10 June 2021 | Toggle abstract · pdf

A critical question concerning generative networks applied to event generation in particle physics is if the generated events add statistical precision beyond the training sample. We show for a simple example with increasing dimensionality how generative networks indeed amplify the training statistics. We quantify their impact through an amplification factor or equivalent numbers of sampled events.

Sascha Diefenbacher, Hermann Frost, Gregor Kasieczka, Tilman Plehn, Jennifer M. Thompson

SciPost Phys. 8, 023 (2020) · published 7 February 2020 | Toggle abstract · pdf

Capsule networks are ideal tools to combine event-level and subjet information at the LHC. After benchmarking our capsule network against standard convolutional networks, we show how multi-class capsules extract a resonance decaying to top quarks from both, QCD di-jet and the top continuum backgrounds. We then show how its results can be easily interpreted. Finally, we use associated top-Higgs production to demonstrate that capsule networks can work on overlaying images to go beyond calorimeter information.

Martin Bauer, Sascha Diefenbacher, Tilman Plehn, Michael Russell, Daniel A. Camargo

SciPost Phys. 5, 036 (2018) · published 19 October 2018 | Toggle abstract · pdf

A consistent model for vector mediators to dark matter needs to be anomaly-free and include a scalar mode from mass generation. For the leading U(1) extensions we review the structure and constraints, including kinetic mixing at loop level. The thermal relic density suggests that the vector and scalar masses are similar. For the LHC we combine a $Z'$ shape analysis with mono-jets. For the latter, we find that a shape analysis offers significant improvement over existing cut-and-count approaches. Direct detection limits strongly constrain the kinetic mixing angle and we propose a $\ell^+\ell^- E_T$ search strategy based on the scalar mediator.