18.06.17 - 23.06.17, Seminar 17251

Game Theory Meets Computational Learning Theory

The following text appeared on our web pages prior to the seminar, and was included as part of the invitation.


There is already a rich history of interaction between machine learning and game theory and economics. At present, there is increasing activity at this intersection, due to the emergence of novel and interesting theory challenges, often coupled with compelling practical motivations. Of course, this activity is motivated by the increasing quantity of data arising from various economic and social interactions. A rigorous theoretical understanding of the interplay of game theory and learning theory is a key requirement for mastering this wealth of data.

This Dagstuhl Seminar will bring together leading researchers from computer science and economics, with expertise in (algorithmic) game theory and computational learning theory. The expected outcome of the seminar is a coordinated effort to

  1. explore and formulate key questions and open problems at the intersection of the two fields,
  2. identify concrete approaches and techniques from the two fields that bear the potential to advance the state of the art in the other field, and
  3. combine tools from both fields to provide the necessary theoretical tools to study learning in strategic environments.

Illustrative research challenges include (but are not restricted to) the following:

  1. sample complexity for revenue maximization in various settings including (Bayesian) mechanism design,
  2. preference elicitation from economic behavior,
  3. complexity of equilibria, such as query complexity,
  4. models and algorithms for coordinated learning, and
  5. dynamics of multiple agents, for example in social networks.

Besides short technical presentations, we envisage a small number of keynote talks, and discussion groups on more specific subtopics, leading to a panel discussion towards the end of the seminar.

Creative Commons BY 3.0 Unported license
Paul W. Goldberg