2014 COLT COLT 2014

Elicitation and Identification of Properties

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.

🌉 Interdisciplinary Bridge — Machine Learning and Mathematics & Optimization
📈 Trend Setter — Loss Functions
🧭 Keyword Pioneer — elicitable property
🐝 Cross-Pollinator — Artificial Intelligence, Machine Learning, Mathematics & Optimization
🐣 Hot Topic Early Bird — probabilistic modeling