Automated design of scoring rules by learning from examples

Authors:
Ariel D. Procaccia;Aviv Zohar;Jeffrey S. Rosenschein
Affiliations:
The Hebrew University of Jerusalem, Jerusalem, Israel;The Hebrew University of Jerusalem, Jerusalem, Israel;The Hebrew University of Jerusalem, Jerusalem, Israel
Venue:
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 2
Year:
2008

Citing 14
Cited 2

Algorithms in combinatorial geometry

Algorithms in combinatorial geometry
Machine learning: a theoretical approach

Machine learning: a theoretical approach
An automated meeting scheduling system that utilizes user preferences

AGENTS '97 Proceedings of the first international conference on Autonomous agents
Voting for movies: the anatomy of a recommender system

Proceedings of the third annual conference on Autonomous Agents
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
Applying learning algorithms to preference elicitation

EC '04 Proceedings of the 5th ACM conference on Electronic commerce
An Algorithm for Automatically Designing Deterministic Mechanisms without Payments

AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1
Communication complexity of common voting rules

Proceedings of the 6th ACM conference on Electronic commerce
Learning from revealed preference

EC '06 Proceedings of the 7th ACM conference on Electronic commerce
When are elections with few candidates hard to manipulate?

Journal of the ACM (JACM)
On the robustness of preference aggregation in noisy environments

Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Learning voting trees

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Junta distributions and the average-case complexity of manipulating elections

Journal of Artificial Intelligence Research
Complexity of mechanism design

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence

Towards a theory of incentives in machine learning

ACM SIGecom Exchanges
On the approximability of Dodgson and Young elections

SODA '09 Proceedings of the twentieth Annual ACM-SIAM Symposium on Discrete Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

Scoring rules are a broad and concisely-representable class of voting rules which includes, for example, Plurality and Borda. Our main result asserts that the class of scoring rules, as functions from preferences into candidates, is efficiently learnable in the PAC model. We discuss the applications of this result to automated design of scoring rules. We also investigate possible extensions of our approach, and (along the way) we establish a lemma of independent interest regarding the number of distinct scoring rules.