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.

[1]  Gil Kalai.  Learnability and rationality of choice , 2003, J. Econ. Theory.

[2]  Sandip Sen,et al.  An automated meeting scheduling system that utilizes user preferences , 1997, AGENTS '97.

[3]  Vincent Conitzer,et al.  Complexity of Mechanism Design , 2002, UAI.

[4]  David C. Parkes,et al.  Applying learning algorithms to preference elicitation , 2004, EC '04.

[5]  Vincent Conitzer,et al.  Complexity of manipulating elections with few candidates , 2002, AAAI/IAAI.

[6]  Herbert Edelsbrunner,et al.  Algorithms in Combinatorial Geometry , 1987, EATCS Monographs in Theoretical Computer Science.

[7]  H. Young.  Social Choice Scoring Functions , 1975 .

[8]  Ariel D. Procaccia,et al.  Junta Distributions and the Average-Case Complexity of Manipulating Elections , 2007, J. Artif. Intell. Res..

[9]  Ariel D. Procaccia,et al.  On the robustness of preference aggregation in noisy environments , 2007, AAMAS '07.

[10]  Vincent Conitzer,et al.  When are elections with few candidates hard to manipulate? , 2007, J. ACM.

[11]  Vincent Conitzer,et al.  An algorithm for automatically designing deterministic mechanisms without payments , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[12]  Ariel D. Procaccia,et al.  Learning Voting Trees , 2007, AAAI.

[13]  Robert J. Vanderbei,et al.  Linear Programming: Foundations and Extensions , 1998, Kluwer international series in operations research and management service.

[14]  B. Natarajan.  Machine Learning: A Theoretical Approach , 1992 .

[15]  Rakesh V. Vohra,et al.  Learning from revealed preference , 2006, EC '06.

[16]  Sandip Sen,et al.  Voting for movies: the anatomy of a recommender system , 1999, AGENTS '99.

[17]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[18]  Vincent Conitzer,et al.  How many candidates are needed to make elections hard to manipulate? , 2003, TARK '03.

[19]  Vincent Conitzer,et al.  Communication complexity of common voting rules , 2005, EC '05.