Elicitation and Identification of Properties

[edit]

Ingo Steinwart, Chloé Pasin, Robert Williamson, Siyu Zhang ;
Proceedings of The 27th Conference on Learning Theory, PMLR 35:482-526, 2014.

Abstract

Properties of distributions are real-valued functionals such as the mean, quantile or conditional value at risk. A property is elicitable if there exists a scoring function such that minimization of the associated risks recovers the property. We extend existing results to characterize the elicitability of properties in a general setting. We further relate elicitability to identifiability (a notion introduced by Osband) and provide a general formula describing all scoring functions for an elicitable property. Finally, we draw some connections to the theory of coherent risk measures.

Related Material