Convex Elicitation of Continuous Properties
Jessica Finocchiaro · Rafael Frongillo

Wed Dec 5th 10:40 -- 10:45 AM @ Room 517 CD

A property or statistic of a distribution is said to be elicitable if it can be expressed as the minimizer of some loss function in expectation. Recent work shows that continuous real-valued properties are elicitable if and only if they are identifiable, meaning the set of distributions with the same property value can be described by linear constraints. From a practical standpoint, one may ask for which such properties do there exist convex loss functions. In this paper, in a finite-outcome setting, we show that in fact every elicitable real-valued property can be elicited by a convex loss function. Our proof is constructive, and leads to convex loss functions for new properties.

Author Information

Jessie Finocchiaro (University of Colorado Boulder)
Rafael Frongillo (CU Boulder)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors