DagSemProc.07271.6.pdf
- Filesize: 139 kB
- 13 pages
Document
Incentive Compatible Regression Learning
Authors
-
Part of:
Volume:
Dagstuhl Seminar Proceedings, Volume 7271
Series: Dagstuhl Seminar Proceedings (DagSemProc) - License:
Creative Commons Attribution 4.0 International license
- Publication Date: 2007-10-02
Cite AsGet BibTex
Ofer Dekel, Felix Fischer, and Ariel D. Procaccia. Incentive Compatible Regression Learning. In Computational Social Systems and the Internet. Dagstuhl Seminar Proceedings, Volume 7271, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2007)
https://doi.org/10.4230/DagSemProc.07271.6
https://doi.org/10.4230/DagSemProc.07271.6
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.
Keywords
- Machine learning
- regression
- mechanism design
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads