fimos 2011 - NIPS-2011 Workshop on New Frontiers in Model Order Selection

New Frontiers in Model Order Selection
NIPS-2011 Workshop, Sierra Nevada,Granada, Spain,
December 16, 2011
http://people.kyb.tuebingen.mpg.de/seldin/fimos.ht...

UPDATE

New deadline: October 24!

DESCRIPTION

Model order selection, which is a trade-off between model complexity and its empirical data fit, is one of the fundamental questions in machine learning. It was studied in detail in the context of supervised learning with i.i.d. samples, but received relatively little attention beyond this domain. The goal of our workshop is to raise attention to the question of model order selection in other domains, share ideas and approaches between the domains, and identify perspective directions for future research. Our interest covers ways of defining model complexity in different domains, examples of practical problems, where intelligent model order selection yields advantage over simplistic approaches, and new theoretical tools for analysis of model order selection. The domains of interest span over all problems that cannot be directly mapped to supervised learning with i.i.d. samples, including, but not limited to, reinforcement learning, active learning, learning with delayed, partial, or indirect feedback, and learning with submodular functions.

An example of first steps in defining complexity of models in reinforcement learning, applying trade-off between model complexity and empirical performance, and analyzing it can be found in [1-4]. An intriguing research direction coming out of these works is simultaneous analysis of exploration-exploitation and model order selection trade-offs. Such an analysis enables to design and analyze models that adapt their complexity as they continue to explore and observe new data. Potential practical applications of such models include contextual bandits (for example, in personalization of recommendations on the web [5]) and Markov decision processes.

References:
[1] N. Tishby, D. Polani. "Information Theory of Decisions and Actions", Perception-Reason-Action Cycle: Models, Algorithms and Systems, 2010.
[2] J. Asmuth, L. Li, M. L. Littman, A. Nouri, D. Wingate, "A Bayesian Sampling Approach to Exploration in Reinforcement Learning", UAI, 2009.
[3] N. Srinivas, A. Krause, S. M. Kakade, M. Seeger, "Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design", ICML, 2010.
[4] Y. Seldin, N. Cesa-Bianchi, F. Laviolette, P. Auer, J. Shawe-Taylor, J. Peters, "PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off", ICML-2011 workshop on online trading of exploration and exploitation.
[5] A. Beygelzimer, J. Langford, L. Li, L. Reyzin, R. Schapire, "Contextual Bandit Algorithms with Supervised Learning Guarantees", AISTATS, 2011.

CALL FOR ABSTRACTS

We invite submission of abstracts to the workshop. Abstracts should be at most 4 pages long in the NIPS format (appendices are allowed, but the organizers reserve the right to evaluate submissions based on the first 4 pages only). Selected abstracts will be presented as posters during the workshop. Submissions should be sent by email to seldin at tuebingen dot mpg dot de.

Update: Two best abstracts will be presented as contributed talks!

IMPORTANT DATES

Submission Deadline: October 24.
Notification of Acceptance: November 4.

INVITED SPEAKERS

Shie Mannor, Technion
John Langford, Yahoo!
Naftali Tishby, The Hebrew University
Peter Auer, Montanuniversität Leoben

ORGANIZERS

Yevgeny Seldin, Max Planck Institute for Intelligent Systems
Koby Crammer, Technion
Nicolò Cesa-Bianchi, University of Milano
François Laviolette, Université Laval
John Shawe-Taylor, University College London