H-Consistency Bounds: Characterization and Extensions

A series of recent publications by Awasthi, Mao, Mohri, and Zhong [2022b] have introduced the key notion of H-consistency bounds for surrogate loss functions. These are upper bounds on the zero-one estimation error of any predictor in a hypothesis set, expressed in terms of its surrogate loss estimation error. They are both non-asymptotic and hypothesis set-specific and thus stronger and more informative than Bayes-consistency. However, determining if they hold and deriving these bounds have required a specific proof and analysis for each surrogate loss. Can we derive more general tools and characterizations?