Creative Commons Attribution 4.0 license (CC BY 4.0)when quoting this document, please refer to the following
DOI: 10.4230/DagSemProc.07271.6
URN: urn:nbn:de:0030-drops-11622
URL: https://drops.dagstuhl.de/opus/volltexte/2007/1162/
Dekel, Ofer ; Fischer, Felix ; Procaccia, Ariel D.
Incentive Compatible Regression Learning
| pdf-format: |
|
Abstract
We initiate the study of incentives in a general machine learning framework. We focus on a game theoretic regression learning setting where private information is elicited from multiple agents, which are interested in different distributions over the sample space. This conflict potentially gives rise to untruthfulness on the part of the agents. In the restricted but important case when distributions are degenerate, and under mild assumptions, we show that agents are motivated to tell the truth. In a more general setting, we study the power and limitations of mechanisms without payments. We finally establish that, in the general setting, the VCG mechanism goes a long way in guaranteeing truthfulness and efficiency.
BibTeX - Entry
@InProceedings{dekel_et_al:DagSemProc.07271.6,
author = {Dekel, Ofer and Fischer, Felix and Procaccia, Ariel D.},
title = {{Incentive Compatible Regression Learning}},
booktitle = {Computational Social Systems and the Internet},
series = {Dagstuhl Seminar Proceedings (DagSemProc)},
ISSN = {1862-4405},
year = {2007},
volume = {7271},
editor = {Peter Cramton and Rudolf M\"{u}ller and Eva Tardos and Moshe Tennenholtz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/opus/volltexte/2007/1162},
URN = {urn:nbn:de:0030-drops-11622},
doi = {10.4230/DagSemProc.07271.6},
annote = {Keywords: Machine learning, regression, mechanism design}
}
| Keywords: | Machine learning, regression, mechanism design | |
| Seminar: | 07271 - Computational Social Systems and the Internet | |
| Issue date: | 2007 | |
| Date of publication: | 02.10.2007 |
