Learning Minimal-Deviation Corrections for Multi-Dimensional Mismodelling in HEP Simulations
For high-energy physicists, this provides a scalable correction method when only 1D data are available, addressing a practical bottleneck in simulation-based analyses.
The paper proposes a neural network method that corrects multi-dimensional mismodelling in HEP simulations using only 1D target distributions, preserving the correlation structure of the original simulation. In controlled studies, it improves agreement with target distributions while maintaining consistent multidimensional structure.
Accurate Monte Carlo (MC) modelling in high-energy physics is challenging, particularly in complex scenarios where simulations fail to reproduce observed data. In practice, experimental information is often limited to one-dimensional (1D) distributions, while mismodelling arises in a multidimensional feature space. This restricts traditional correction methods, as one-dimensional reweighting ignores correlations and fully multidimensional approaches require large target datasets. We propose a neural network-based method that operates under these constraints by learning a transformation of simulated events that reproduces the available 1D target distributions while remaining close to the original simulation. This minimal-deviation principle preserves the global correlation structure of the baseline model while enabling targeted corrections of mismodelled features. Using controlled studies with simulated pseudo-data, we show that the method improves agreement with target distributions and maintains a consistent multidimensional structure. The approach is designed for complex, high-dimensional analyses where traditional techniques are insufficient, providing a scalable way to enhance MC modelling under limited information.