{q}unfold: Composable Quantification and Unfolding Methods in {P}ython

We present qunfold, a Python package that implements several quantification and unfolding methods. A unique capability of qunfold is the composition of novel methods from existing and easily customized loss functions and data representations. Moreover, this package leverages a powerful optimization back-end to yield state-of-the-art performances for all compositions. This paper introduces the common usage patterns for qunfold, revisits the technical background of the package, and empirically demonstrates the resulting performance.

  • Published in:
    International Workshop on Learning to Quantify
  • Type:
    Inproceedings
  • Authors:
    Bunse, Mirko
  • Year:
    2023

Citation information

Bunse, Mirko: {q}unfold: Composable Quantification and Unfolding Methods in {P}ython, International Workshop on Learning to Quantify, 2023, 1--7, September, https://lq-2023.github.io/proceedings/CompleteVolume.pdf, Bunse.2023a,