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.
Original language | English |
---|---|
Pages (from-to) | 482-526 |
Number of pages | 45 |
Journal | Journal of Machine Learning Research |
Volume | 35 |
Publication status | Published - 2014 |
Event | 27th Conference on Learning Theory, COLT 2014 - Barcelona, Spain Duration: 13 Jun 2014 → 15 Jun 2014 |