Contributor info: Dr Henning Bahl

Henning Bahl, Nina Elmer, Luigi Favaro, Manuel Haußmann, Tilman Plehn, Ramon Winterhalder

SciPost Phys. Core 8, 073 (2025) · published 24 October 2025 | Toggle abstract · pdf

Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with Kolmogorov-Arnold Networks. Then, we train neural surrogates to simultaneously predict the target amplitude and an uncertainty for the prediction. We disentangle systematic uncertainties, learned by a well-defined likelihood loss, from statistical uncertainties, which require the introduction of Bayesian neural networks or repulsive ensembles. We test the coverage of the learned uncertainties using pull distributions to quantify the calibration of cutting-edge neural surrogates.

Henning Bahl, Victor Bresó-Pla, Giovanni De Crescenzo, Tilman Plehn

SciPost Phys. Core 8, 060 (2025) · published 29 September 2025 | Toggle abstract · pdf

We study the benefit of modern simulation-based inference to constrain particle interactions at the LHC. We explore ways to incorporate known physics structures into likelihood estimation, specifically morphing-aware estimation and derivative learning. Technically, we introduce a new and more efficient smearing algorithm, illustrate how uncertainties can be approximated through repulsive ensembles, and show how equivariant networks can improve likelihood estimation. After illustrating these aspects for a toy model, we target di-boson production at the LHC and find that our improvements significantly increase numerical control and stability.

Henning Bahl, Elina Fuchs, Marc Hannig, Marco Menen

SciPost Phys. Core 8, 006 (2025) · published 20 January 2025 | Toggle abstract · pdf

The Higgs-gluon interaction is crucial for LHC phenomenology. To improve the constraints on the $\mathcal{CP}$ structure of this coupling, we investigate Higgs production with two jets using machine learning. In particular, we exploit the $\mathcal{CP}$ sensitivity of the so far neglected phase space region that differs from the typical vector boson fusion-like kinematics. Our results indicate that further improvements in the current experimental limits could be achievable using our techniques. We also discuss the most relevant observables and how $\mathcal{CP}$ violation in the Higgs–gluon interaction can be disentangled from $\mathcal{CP}$ violation in the interaction between the Higgs boson and massive vector bosons. Assuming the absence of $\mathcal{CP}$-violating Higgs interactions with coloured beyond-the-Standard-Model states, our projected limits on a $\mathcal{CP}$-violating top-Yukawa coupling are competitive with more direct probes like top-associated Higgs production and limits from a global fit.

Henning Bahl

SciPost Phys. Proc. 8, 010 (2022) · published 11 July 2022 | Toggle abstract · pdf

Precision measurements of top-associated Higgs production are an important ingredient to unravel the $\mathcal{CP}$ nature of the Higgs boson. In this work, we constraint the $\mathcal{CP}$ nature of the top-Yukawa coupling taking into account all relevant inclusive and differential Higgs boson measurements. Based upon this fit, we show that it is crucial to disentangle single- and di-top-associated Higgs production for tightening indirect constraints on a $\mathcal{CP}$-odd top-Yukawa coupling in the future. In this context, we propose an analysis strategy for measuring $tH$ production at the HL-LHC without relying on assumptions about the Higgs $\mathcal{CP}$ character.