Speaker
Description
Simulation-based inference (SBI) is a set of statistical inference approaches in which Machine Learning (ML) algorithms are trained to approximate likelihood ratios. It has been shown to provide an alternative to the likelihood fits commonly performed in HEP analyses. SBI is particularly attractive in analyses performed over many dimensions, in which binning data would be computationally infeasible or would result in a loss of sensitivity.
In this work, SBI is applied to extract parameters of interest from the kinematic and angular distributions of $B^0 \to D^{\ast-}\mu^{+}\nu_\mu$ decays at LHCb, in pseudodata samples generated with RapidSim representative of the datasets used in LHCb analysis. The SBI fit is constructed using the RooFit framework, to which enhanced Python interfaces were recently introduced. Dense Neural Networks (DNNs) were trained to distinguish between the Standard Model and New Physics scenarios for varying parameters of interest. This workflow also incorporates the automatic differentiation (AD) of learned likelihoods, using the ROOT SOFIE framework to generate C++ code from the DNNs, from which gradient code is generated by source-code transformation AD with the Clad compiler plugin.
In this contribution, the SBI fit is compared to an equivalent template-based likelihood fit reflecting the current state-of-the-art. These fits are compared both in terms of statistical sensitivity and computational performance. Additionally, this contribution presents a direct application of AD to physics analysis.
References
New RooFit PyROOT interfaces for connections with Machine Learning, J. Rembser, et al., CHEP 2024, Oct. 2024: https://indico.cern.ch/event/1338689/contributions/6016195/
Significance
This contribution presents the first concrete example of an application of simulation-based inference to parameter estimation in LHCb analysis. The motivation for developing such a framework is introduced and the framework is evaluated against the current state-of-the-art template-based fitter. This work uniquely combines recent R&D in the ROOT framework: in RooFit, TMVA SOFIE and Clad, to build fully differentiable likelihoods incorporating neural networks as likelihood surrogates.
| Experiment context, if any | LHCb |
|---|
