PAC Learning and Stabilizing Hedonic Games: Towards a Unifying Approach.

Learning Hedonic Games

Coalitional stability in hedonic games has usually been considered in the setting where agent preferences are fully known. We consider the setting where agent preferences are unknown; we lay the theoretical foundations for studying the interplay between coalitional stability and (PAC) learning in hedonic games. We introduce the notion of PAC stability — the equivalent of core stability under un...

Towards Structural Tractability in Hedonic Games

Hedonic games are a well-studied model of coalition formation, in which selfish agents are partitioned into disjoint sets, and agents care about the make-up of the coalition they end up in. The computational problem of finding a stable outcome tends to be computationally intractable, even after severely restricting the types of preferences that agents are allowed to report. We investigate a str...

A PAC-Bayesian Approach to Structure Learning

Structure learning is an important sub-domain of machine learning. Its goal is a high level understanding of the data. For example, given an image as a collection of pixels, the goal is to identify the objects present in the image, such as people, trees, birds, to infer their actions (e.g., standing, flying) and interactions (e.g. a man is feeding a bird). Structure learning has multiple applic...

Statistical Learning Theory: A PAC-Bayesian Approach

Hedonic Games

Coalitions are a central part of economic, political, and social life, and coalition formation has been studied extensively within the mathematical social sciences. Agents (be they humans, robots, or software agents) have preferences over coalitions and, based on these preferences, it is natural to ask which coalitions are expected to form, and which coalition structures are better social outco...