An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative training
This work addresses the challenge of accurate data-to-theory comparisons in particle physics by improving unfolding techniques, though it appears incremental as it builds on existing generative network methods.
The authors tackled the problem of unfolding detector effects in high-energy physics by introducing an iterative conditional invertible neural network (IcINN) that adjusts for deviations between simulated training samples and actual data, achieving validation on toy data and application to the pp → Z γγ process.
The unfolding of detector effects is crucial for the comparison of data to theory predictions. While traditional methods are limited to representing the data in a low number of dimensions, machine learning has enabled new unfolding techniques while retaining the full dimensionality. Generative networks like invertible neural networks~(INN) enable a probabilistic unfolding, which map individual events to their corresponding unfolded probability distribution. The accuracy of such methods is however limited by how well simulated training samples model the actual data that is unfolded. We introduce the iterative conditional INN~(IcINN) for unfolding that adjusts for deviations between simulated training samples and data. The IcINN unfolding is first validated on toy data and then applied to pseudo-data for the $pp \to Z γγ$ process.