June 18 – 23 , 2017, Dagstuhl Seminar 17251

Game theory meets computational learning theory


Maria-Florina Balcan (Carnegie Mellon University – Pittsburgh, US)
Paul W. Goldberg (University of Oxford, GB)
Michael J. Kearns (University of Pennsylvania – Philadelphia, US)
Yishay Mansour (Tel Aviv University, IL)


Paul Dütting (London School of Economics, GB)

For support, please contact

Simone Schilke for administrative matters

Andreas Dolzmann for scientific matters


Dagstuhl Seminar Schedule (Upload here)

(Use seminar number and access code to log in)


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

(a) explore and formulate key questions and open problems at the intersection of the two fields,

(b) 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

(c) 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 DE
  Paul W. Goldberg


  • Data Structures / Algorithms / Complexity


  • Theory
  • Algorithms and complexity
  • Computational learning
  • Game theory

Book exhibition

Books from the participants of the current Seminar 

Book exhibition in the library, ground floor, during the seminar week.


In the series Dagstuhl Reports each Dagstuhl Seminar and Dagstuhl Perspectives Workshop is documented. The seminar organizers, in cooperation with the collector, prepare a report that includes contributions from the participants' talks together with a summary of the seminar.


Download overview leaflet (PDF).


Furthermore, a comprehensive peer-reviewed collection of research papers can be published in the series Dagstuhl Follow-Ups.

Dagstuhl's Impact

Please inform us when a publication was published as a result from your seminar. These publications are listed in the category Dagstuhl's Impact and are presented on a special shelf on the ground floor of the library.