Social choice theory is the field that studies the aggregation of individual preferences toward a collective choice. While the artificial intelligence (AI) community has so far played a dominant role in the study of the computational aspects of social choice, the interaction between core AI paradigms and social choice theory has been surprisingly limited.
This project is enhancing the interaction between the two fields through a synthesis of social choice with the following AI areas: (i) decision making under uncertainty, by building on models studied in AI to create new ways to model, analyze, and make decisions in environments where preferences are dynamically changing; (ii) multiagent systems, by studying settings where agents randomly vote over multiple states, and investigating the connection between normative properties and system performance; and finally (iii) machine learning, by employing insights about strategic behavior under structured preferences, developed in the social choice literature, in order to design regression learning algorithms that discourage strategic manipulation.
An overarching goal of this project is to demonstrate the potential of social choice theory to AI researchers, and ultimately to establish social choice theory as a standard paradigm in AI. Equally importantly, this project is expected to increase the scope of social choice theory. Broader impacts include a new web-based voting system, which has the potential to serve and educate hundreds of thousands of users; dissemination through a new book on computational social choice; and a workshop on computational social choice, which will help set a new agenda for the field.
