Apologies for cross posting
NIPS 2016 Workshop:

Barcelona, Spain
December 9, 2016
Workshop web: http://www.utia.cz/imperfectDM


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


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
David H. Wolpert, Santa Fe Institute, USA


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:

o Does the concept of rationality require Bayesian reasoning?
o Does quantum probability theory (extending classical Kolmogorov
probability) provide novel insights into the relation between decision
making and cognition?
o 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?
o How can good (meta-)heuristics, so successfully used by real-world decision makers, be elicited?

The next open list indicates possible TOPICS:
- aspects of real DM poorly reflected by prescriptive DM theories
- non-trivial case studies revealing decisive aspects of real DM
- inspiring features of human/animals/societal DM
- ways adopted by brain for solving complex DM
- role and structure of efficient heuristics in DM
- questionable or missing concepts and assumptions in prescriptive DM
- role of memory structure or forgetting in prescriptive DM
- prescriptive multi-participant DM in cooperative and competitive scenarios
- modelling of participants' "power" influencing multi-participant DM

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.


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.


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.


All accepted submissions will be published in vol.58 of 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:
d...@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.

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


Tatiana V. Guy (CZ)
Miroslav Karny (CZ)
David Rios Insua (ES)
David H. Wolpert (USA)


You can reach the organizers at: d...@utia.cas.cz
Workshop web: http://www.utia.cz/imperfectDM
Main Conference webpage: http://nips.cc/

uai mailing list

Reply via email to