Incentive compatible regression learning

Authors:
Ofer Dekel;Felix Fischer;Ariel D. Procaccia
Affiliations:
Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA;Harvard SEAS, 33 Oxford Street, Cambridge, MA 02138, USA;Harvard SEAS, 33 Oxford Street, Cambridge, MA 02138, USA
Venue:
Journal of Computer and System Sciences
Year:
2010

Citing 14
Cited 7

Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow

COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Learning in the presence of malicious errors

SIAM Journal on Computing
Decision theoretic generalizations of the PAC model for neural net and other learning applications

Information and Computation
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Truth revelation in approximately efficient combinatorial auctions

Journal of the ACM (JACM)
PAC learning with nasty noise

Theoretical Computer Science
Rademacher and gaussian complexities: risk bounds and structural results

The Journal of Machine Learning Research
Can machine learning be secure?

ASIACCS '06 Proceedings of the 2006 ACM Symposium on Information, computer and communications security
Truthful randomized mechanisms for combinatorial auctions

Proceedings of the thirty-eighth annual ACM symposium on Theory of computing
Reducing mechanism design to algorithm design via machine learning

Journal of Computer and System Sciences
Thirteen Reasons Why the Vickrey-Clarke-Groves Process Is Not Practical

Operations Research
The learnability of voting rules

Artificial Intelligence
Zara Uses Operations Research to Reengineer Its Global Distribution Process

Interfaces
Inventory Management of a Fast-Fashion Retail Network

Operations Research

Mix and match

Proceedings of the 11th ACM conference on Electronic commerce
Sum of us: strategyproof selection from the selectors

Proceedings of the 13th Conference on Theoretical Aspects of Rationality and Knowledge
Tight bounds for strategyproof classification

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Algorithms for strategyproof classification

Artificial Intelligence
Mechanism design on discrete lines and cycles

Proceedings of the 13th ACM Conference on Electronic Commerce
Strategyproof facility location and the least squares objective

Proceedings of the fourteenth ACM conference on Electronic commerce
Approximate Mechanism Design without Money

ACM Transactions on Economics and Computation

Quantified Score

Hi-index	0.00

Visualization

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 with different, possibly conflicting, views on how to label the points of an input space. This conflict potentially gives rise to untruthfulness on the part of the agents. In the restricted but important case when every agent cares about a single point, 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 economic efficiency.