SCALABLE DECISION MAKING: UNCERTAINTY, IMPERFECTION, DELIBERATION
a workshop in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2013)

September 23, 2013, Prague, Czech Republic

http://www.utia.cz/ECMLHome
--------------------------------------------------------------------------------------

Important Dates:

Submission of papers due July 7, 2013
Notification of acceptance: July 19, 2013
Submission of the camera-ready due August 2, 2013
--------------------------------------------------------------------------------------
DESCRIPTION

Machine learning (ML) and knowledge discovery both use and serve to decision making (DM), which has to cope with uncertainty, incomplete knowledge, problem and data complexity and imperfection (limited cognitive and evaluating capabilities) of the involved heterogeneous multiple participants (aka agents, decision makers, components, controllers, classifiers, etc.). Contemporary DM deals with complex systems characterised by heterogeneous components and their goal-motivated dynamic interactions. The individual participants are selfish, i.e. follow their individual goals. There is no well-justified way how to influence or describe the resulting collective behaviour of such a system via a well-proved combination of the selfish components. Economic and natural sciences describe concepts governing the functioning of systems of selfish participants as well as ways influencing their behaviour. However, the majority of solutions rely on the human moderator/manager controlling such a system. Sophisticated ML and AI solutions developed consider artificial moderators (for instance, automatic traders used in markets, e-democracy support) as well.

Without moderator, decision making with imperfect selfish decision makers lacks a firm prescriptive basis. This problem emerges repeatedly and has no easy solution. While the theoretical, algorithmic and application achievements are immense, real-life complex problems uncover discrepancies between normative and descriptive theories. This clearly indicates the need for alternative ways, deepening and unifying the current achievements across scientific schools as well as research domains. For instance, i) the consistent theory of incomplete Bayesian games cannot be applied by imperfect participants; ii) a desirable incorporation of “deliberation effort” into the design of decision-making strategies remains unsolved. At the same time real societal, biological, economical systems efficiently cope with the imperfectness as confirmed by numerous descriptive studies. Driven by complexity, these systems exhibit a kind of (self-organising) behaviour without any intrinsic utility. This can be viewed as a result of an external control towards a common goal.

The workshop generally aims to exploit the knowledge and experience of multi-disciplinary scientific community and to extract a set of fundamental concepts describing a phenomenon of dynamic decision making with interacting imperfect selfish participants. Devices (e.g. robots), computer algorithms (e.g. controllers), humans (e.g. experts) and their combination will be considered.

TARGETED AUDIENCE:

-- Machine learning, artificial intelligence, complex systems, knowledge discovery and DM related communities
-- Scientists and students from the different scientific communities (decision science, cognitive science, natural science, social science, engineering, etc.) interested in various aspects of decision making.

FORMAT

This is a one-day workshop in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (http://www.ecmlpkdd2013.org/).
The workshop will be based on invited talks, contributed talks and posters. Extensive moderated and informal discussions will ensure the targeted information exchange.

CONFIRMED INVITED TALKS (in alphabetical order)

David Rios Insua, Royal Academy of Sciences, Spain
Miroslav Kárný, Institute of Information Theory and Automation, Czech Republic
Stephen Roberts, University of Oxford, United Kingdom
Naftali Tishby, The Hebrew University, Israel
Alessandro E.P. Villa, University of Lausanne, Switzerland

PAPER SUBMISSION

Submissions should be within the range 8 - 12 pages formatted using LNCS style available at http://www.springer.com/computer/lncs/lncs+authors.
Submitted papers will be reviewed. Acceptance will be based on relevance, technical soundness, originality, and clarity of presentation. Accepted papers will be published in the workshop proceedings.

Please note that one author of each accepted paper must present the paper at the workshop. Papers that have previously appeared (or have been accepted for publication) in a journal or at a conference/workshop are not appropriate for the workshop.

Post-proceedings to be published by Springer
The authors of workshop contributions are invited to submit an extended version (20-30 pages) of their work for publication in an edited book to be published by Springer.
An additional review process is intended to ensure the expected high quality of the submitted manuscripts.



PROGRAMME COMMITTEE (confirmed, in alphabet order):

Henry Brighton, Max Planck Institute for Human Development, Berlin, Germany
Itzhak Gilboa, HEC, Paris, France
Robert J.Howlett, KES International, UK
Miroslav Kárný, Institute of Information Theory and Automation, Prague
Adrian Raftery, University of Washington, USA
Fabrizio Ruggeri, Institute of Applied Mathematics and Information Technology, Milano, Italy
Václav Šmídl, Institute of Information Theory and Automation, Prague
David H.Wolpert, Santa Fe Institute, USA

WORKSHOP ORGANISERS:

T.V. Guy, Institute of Information Theory and Automation, Czech Republic
M. Kárný, Institute of Information Theory and Automation, Czech Republic

CONTACTS
You can reach the organisers at imperfectDM@utia.cas.cz
Workshop web page: http://www.utia.cz/ECMLHome
Main Conference webpage: http://www.ecmlpkdd2013.org/