Effective LHC measurements with matrix elements and machine learning
This work addresses a major bottleneck in particle physics analyses at the LHC, offering incremental improvements through hybrid methods.
The paper tackles the challenge of intractable likelihood functions in high-dimensional LHC data by reviewing traditional and modern inference methods, and proposes new techniques combining matrix elements and machine learning, which show potential for substantially improving measurement sensitivity.
One major challenge for the legacy measurements at the LHC is that the likelihood function is not tractable when the collected data is high-dimensional and the detector response has to be modeled. We review how different analysis strategies solve this issue, including the traditional histogram approach used in most particle physics analyses, the Matrix Element Method, Optimal Observables, and modern techniques based on neural density estimation. We then discuss powerful new inference methods that use a combination of matrix element information and machine learning to accurately estimate the likelihood function. The MadMiner package automates all necessary data-processing steps. In first studies we find that these new techniques have the potential to substantially improve the sensitivity of the LHC legacy measurements.