------------------------------------------------------------------------------------
IMPERFECT DECISION MAKERS: ADMITTING REAL-WORLD RATIONALITY
a workshop in conjunction with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016).

December 9, 2016
Centre Convencions Internacional, Barcelona, Spain

Email: dm@utia.cas.cz
Workshop webpage: http://www.utia.cz/imperfectDM

------------------------------------------------------------------------------------
Important Dates:

Submission Deadline: October 21, 2016
Notification of acceptance: November 11, 2016
Submission of the final version due: November 25, 2016
------------------------------------------------------------------------------------

DESCRIPTION

The prescriptive (normative) Bayesian theory of decision making under uncertainty has reached a high level of maturity. The assumption that the decision maker is rational (i.e. that they optimize expected utility, in Savage’s formulation) is central to this theory. However, empirical research indicates that this central assumption is often violated by real decision-makers. This limits the ability of the prescriptive Bayesian theory to provide a descriptive theory of the real world. One of the reasons that have been proposed for why the assumption of rationality might be violated by real decision makers is the limited cognitive and computational resources of those decision makers. This workshop intends to inspect this core assumption and to consider possible ways to modify or complement it.

Many of the precise issues related to this theme – some of which will be addressed in the invited talks - can be formulated as questions:

• Does the concept of rationality require Bayesian reasoning?
• Does quantum probability theory (extending classical Kolmogorov probability) provide novel insights into the relation between decision making and cognition?
• Do the extensions of expected utility (which is a linear function of the relevant probabilities) to nonlinear functions of probabilities enhance the flexibility of decision-making task formulating while respecting the limited cognitive resources of decision makers? • How can good (meta-)heuristics, so successfully used by real-world decision makers, be elicited?

The list is definitely not complete and we expect that contributed talks, posters and informal discussions will extend it. To stimulate the informal discussions, the invited talks will be complemented by discussants challenging them. Altogether, the workshop aims to bring together diverse scientific communities, to brainstorm possible research directions, and to encourage collaboration among researchers with complementary ideas and expertise. The intended outcome is to understand and diminish the discrepancy between the established prescriptive theory and real-world decision making.

TARGETED AUDIENCE:

The targeted audience is scientists and students from the diverse scientific communities (decision science, cognitive science, natural science, artificial intelligence, machine learning, social science, economics, etc.) interested in various aspects of rationality.

FORMAT

This is a one-day workshop in conjunction the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) (https://nips.cc/).
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)

Daniel Braun, Max Planck Institute for Biological Cybernetics, Germany
Itzhak Gilboa, HEC Paris, France
Tom Griffiths, University Berkeley, USA
Pedro Ortega, University of Pennsylvania, USA
Timothy J. Pleskac,Max Planck Institute for Human Development, Germany
Naftali Tishby, The Hebrew University, Israel

PAPER SUBMISSION

All accepted submissions will be published in the Workshop and Conference Proceedings series of the Journal of Machine Learning Research(JMRL) as well as presented at the workshop as posters and talks. If you do not wish your work to be published in the JMRL proceedings, please indicate that in your submission email.

Submissions should be 8-10 pages in length and should follow the JMLR format. Detailed formatting instructions and formatting templates can be found at http://www.jmlr.org/format/format.html. 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.

Submissions need not to be anonymous and should include the title, authors' names, postal and email addresses, and an abstract not to exceed 150 words. Submissions in pdf format only should be sent to: dm@utia.cas.cz with the subject line "NIPS2016 Workshop" and with the title, authors' names and abstract included in the body of the message. Please, make sure you get a confirmation email after you submit.

Submissions will be peer-reviewed on the basis of technical quality, originality, potential impact, and clarity. The selected submissions may be accepted either as a contributed talk or as a poster presentation.

Two rounds of submission are announced. Please check the deadlines for workshop submissions. Contributions submitted to the first round (deadline September 22, 2016) will receive an acceptance/rejection decision before the NIPS 2016 early registration deadline.

Please note that one author of each accepted paper must present the paper at the workshop.

WORKSHOP ORGANISERS:

Tatiana V. Guy, Institute of Information Theory and Automation, Czech Republic
Miroslav Kárný, Institute of Information Theory and Automation, Czech Republic
David Rios Insua, Royal Academy of Sciences, Spain
David H. Wolpert, Santa Fe Institute, USA

CONTACTS
You can reach the organisers at dm@utia.cas.cz
Workshop webpage: http://www.utia.cz/imperfectDM
Main Conference webpage: http://nips.cc/