Reviews: On Structured Prediction Theory with Calibrated Convex Surrogate Losses

The paper examines consistency of surrogate losses for multiclass prediction. The authors present their results using the formalism of structured prediction. Alas, there is no direct connection or exploitation of the separability of structured prediction losses. The paper is overly notated and variables are frequently overloaded. I got the feeling that the authors are trying to look mathematically fancy at the expense of readability.