Automated design of scoring rules by learning from examples

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. Categories and Subject Descriptors F.2 [Theory of Computation]: Analysis of Algorithms and Problem Complexity; I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence--Multiagent Systems; J.4 [Computer Applications]: Social and Behavioral Sciences--Economics General Terms Algorithms, Theory, Economics Keywords Voting, PAC learning

• Type: Conference
• Year: 2008
• Where: ATAL
• Authors: Ariel D. Procaccia, Aviv Zohar, Jeffrey S. Rosenschein
• Keywords: ATAL 2008, Distinct Scoring Rules, Intelligent Agents, PAC Model, Scoring Rules