Optimum Statistical Estimation with Strategic Data Sources

Yang Cai, Constantinos Daskalakis, Christos Papadimitriou
Proceedings of The 28th Conference on Learning Theory, PMLR 40:280-296, 2015.

Abstract

We propose an optimum mechanism for providing monetary incentives to the data sources of a statistical estimator such as linear regression, so that high quality data is provided at low cost, in the sense that the weighted sum of payments and estimation error is minimized. The mechanism applies to a broad range of estimators, including linear and polynomial regression, kernel regression, and, under some additional assumptions, ridge regression. It also generalizes to several objectives, including minimizing estimation error subject to budget constraints. Besides our concrete results for regression problems, we contribute a mechanism design framework through which to design and analyze statistical estimators whose examples are supplied by workers with cost for labeling said examples.

Cite this Paper


BibTeX
@InProceedings{pmlr-v40-Cai15, title = {Optimum Statistical Estimation with Strategic Data Sources}, author = {Cai, Yang and Daskalakis, Constantinos and Papadimitriou, Christos}, booktitle = {Proceedings of The 28th Conference on Learning Theory}, pages = {280--296}, year = {2015}, editor = {Grünwald, Peter and Hazan, Elad and Kale, Satyen}, volume = {40}, series = {Proceedings of Machine Learning Research}, address = {Paris, France}, month = {03--06 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v40/Cai15.pdf}, url = {https://proceedings.mlr.press/v40/Cai15.html}, abstract = {We propose an optimum mechanism for providing monetary incentives to the data sources of a statistical estimator such as linear regression, so that high quality data is provided at low cost, in the sense that the weighted sum of payments and estimation error is minimized. The mechanism applies to a broad range of estimators, including linear and polynomial regression, kernel regression, and, under some additional assumptions, ridge regression. It also generalizes to several objectives, including minimizing estimation error subject to budget constraints. Besides our concrete results for regression problems, we contribute a mechanism design framework through which to design and analyze statistical estimators whose examples are supplied by workers with cost for labeling said examples.} }
Endnote
%0 Conference Paper %T Optimum Statistical Estimation with Strategic Data Sources %A Yang Cai %A Constantinos Daskalakis %A Christos Papadimitriou %B Proceedings of The 28th Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2015 %E Peter Grünwald %E Elad Hazan %E Satyen Kale %F pmlr-v40-Cai15 %I PMLR %P 280--296 %U https://proceedings.mlr.press/v40/Cai15.html %V 40 %X We propose an optimum mechanism for providing monetary incentives to the data sources of a statistical estimator such as linear regression, so that high quality data is provided at low cost, in the sense that the weighted sum of payments and estimation error is minimized. The mechanism applies to a broad range of estimators, including linear and polynomial regression, kernel regression, and, under some additional assumptions, ridge regression. It also generalizes to several objectives, including minimizing estimation error subject to budget constraints. Besides our concrete results for regression problems, we contribute a mechanism design framework through which to design and analyze statistical estimators whose examples are supplied by workers with cost for labeling said examples.
RIS
TY - CPAPER TI - Optimum Statistical Estimation with Strategic Data Sources AU - Yang Cai AU - Constantinos Daskalakis AU - Christos Papadimitriou BT - Proceedings of The 28th Conference on Learning Theory DA - 2015/06/26 ED - Peter Grünwald ED - Elad Hazan ED - Satyen Kale ID - pmlr-v40-Cai15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 40 SP - 280 EP - 296 L1 - http://proceedings.mlr.press/v40/Cai15.pdf UR - https://proceedings.mlr.press/v40/Cai15.html AB - We propose an optimum mechanism for providing monetary incentives to the data sources of a statistical estimator such as linear regression, so that high quality data is provided at low cost, in the sense that the weighted sum of payments and estimation error is minimized. The mechanism applies to a broad range of estimators, including linear and polynomial regression, kernel regression, and, under some additional assumptions, ridge regression. It also generalizes to several objectives, including minimizing estimation error subject to budget constraints. Besides our concrete results for regression problems, we contribute a mechanism design framework through which to design and analyze statistical estimators whose examples are supplied by workers with cost for labeling said examples. ER -
APA
Cai, Y., Daskalakis, C. & Papadimitriou, C.. (2015). Optimum Statistical Estimation with Strategic Data Sources. Proceedings of The 28th Conference on Learning Theory, in Proceedings of Machine Learning Research 40:280-296 Available from https://proceedings.mlr.press/v40/Cai15.html.

Related Material