Probabilistic coherence and proper scoring rules
Machine Learning
2016-11-15 v1
Abstract
We provide self-contained proof of a theorem relating probabilistic coherence of forecasts to their non-domination by rival forecasts with respect to any proper scoring rule. The theorem appears to be new but is closely related to results achieved by other investigators.
Keywords
Cite
@article{arxiv.0710.3183,
title = {Probabilistic coherence and proper scoring rules},
author = {Joel Predd and Robert Seiringer and Elliott H. Lieb and Daniel Osherson and Vincent Poor and Sanjeev Kulkarni},
journal= {arXiv preprint arXiv:0710.3183},
year = {2016}
}
Comments
LaTeX2, 15 pages