Comments on “Learning from imprecise and fuzzy observations: Data disambiguation through generalized loss minimization” by Eyke Hüllermeier

• Some extension principle-based models are also connected to robust statistics.
• Fuzzy-valued loss functions may be preferred to scalar losses.
• Disambiguation and imputation are close concepts.

The paper by Eyke Hüllermeier introduces a new set of techniques for learning models from imprecise data. The removal of the uncertainty in the training instances through the input–output relationship described by the model is also considered. This discussion addresses three points of the paper: extension principle-based models, precedence operators between fuzzy losses and possible connections between data disambiguation and data imputation.