Open Problem: Property Elicitation and Elicitation Complexity
Abstract
The study of property elicitation is gaining ground in statistics and machine learning as a way to view and reason about the expressive power of emiprical risk minimization (ERM). Yet beyond a widening frontier of special cases, the two most fundamental questions in this area remain open: which statistics are elicitable (computable via ERM), and which loss functions elicit them? Moreover, recent work suggests a complementary line of questioning: given a statistic, how many ERM parameters are needed to compute it? We give concrete instantiations of these important questions, which have numerous applications to machine learning and related fields.
Cite
Text
Frongillo et al. "Open Problem: Property Elicitation and Elicitation Complexity." Annual Conference on Computational Learning Theory, 2016.Markdown
[Frongillo et al. "Open Problem: Property Elicitation and Elicitation Complexity." Annual Conference on Computational Learning Theory, 2016.](https://mlanthology.org/colt/2016/frongillo2016colt-open/)BibTeX
@inproceedings{frongillo2016colt-open,
title = {{Open Problem: Property Elicitation and Elicitation Complexity}},
author = {Frongillo, Rafael M. and Kash, Ian A. and Becker, Stephen},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2016},
pages = {1655-1658},
url = {https://mlanthology.org/colt/2016/frongillo2016colt-open/}
}