Information Geometry and its Applications III

Abstract Peter Harremoës

Go back to

Peter Harremoës  (Copenhagen Business College, Denmark)
Tuesday, August 03, 2010, room Hörsaal 1
Minimum description length for exponential families

A statistical model is essentially an information channel from a parameter space to a data space so that each parameter gives a distribution over possible data. We are interested in characterizing the statistical models that have finite capacity. According to the Gallager-Ryabko Theorem the capacity equals the minimax redundancy. In the minimum description length (MDL) approach to statistics one is interested in the minimax regret rather than the minimax redundancy of the statistical model. The minimax redundancy lower bounds minimax regret so if capacity is infinite the minimax regret is infinite and the MDL approach to statistics fails. In this talk we shall restrict our attention to exponential families. It has been conjectured that finite capacity implies finite minimax regret. We demonstrate that the conjecture holds in 1 dimension but is violated in 3 dimensions. This is joint work with Peter Grünwald.

Date and Location

August 02 - 06, 2010
University of Leipzig
04103 Leipzig

Scientific Organizers

Nihat Ay
Max Planck Institute for Mathematics in the Sciences
Information Theory of Cognitive Systems Group
Contact by Email

Paolo Gibilisco
Università degli Studi di Roma "Tor Vergata"
Facoltà di Economia
Contact by Email

František Matúš
Academy of Sciences of the Czech Republic
Institute of Information Theory and Automation
Czech Republic
Contact by Email

Scientific Committee

Shun-ichi Amari
Brain Science Institute, Mathematical Neuroscience Laboratory
Contact by Email

Imre Csiszár
Hungarian Academy of Sciences
Alfréd Rényi Institute of Mathematics
Contact by Email

Dénes Petz
Budapest University of Technology and Economics
Department for Mathematical Analysis
Contact by Email

Giovanni Pistone
Collegio Carlo Alberto, Moncalieri
Contact by Email

Administrative Contact

Antje Vandenberg
Max Planck Institute for Mathematics in the Sciences
Contact by Email
Phone: (++49)-(0)341-9959-552
Fax: (++49)-(0)341-9959-555

05.04.2017, 12:42