Automated design of scoring rules by learning from examples

Ariel D. Procaccia, Aviv Zohar, Jeffrey S. Rosenschein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

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.

Original languageEnglish
Title of host publication7th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2008
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages933-940
Number of pages8
ISBN (Print)9781605604701
StatePublished - 2008
Event7th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2008 - Estoril, Portugal
Duration: 12 May 200816 May 2008

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume2
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference7th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2008
Country/TerritoryPortugal
CityEstoril
Period12/05/0816/05/08

Keywords

  • PAC learning
  • Voting

Fingerprint

Dive into the research topics of 'Automated design of scoring rules by learning from examples'. Together they form a unique fingerprint.

Cite this