On the axiomatic approach to the maximum entropy principle of inference

Karbelkar, SN (1986) On the axiomatic approach to the maximum entropy principle of inference. In: Pramana, 26 (4). 301 -310.

PDF fulltext.pdf - Published Version Restricted to Registered users only Download (56kB) | Request a copy

Abstract

Recent axiomatic derivations of the maximum entropy principle from consistency conditions are critically examined. We show that proper application of consistency conditions alone allows a wider class of functionals, essentially of the form ∝ dx p(x)[p(x)/g(x)] s , for some real numbers, to be used for inductive inference and the commonly used form − ∝ dx p(x)ln[p(x)/g(x)] is only a particular case. The role of the prior densityg(x) is clarified. It is possible to regard it as a geometric factor, describing the coordinate system used and it does not represent information of the same kind as obtained by measurements on the system in the form of expectation values.

Item Type:	Journal Article
Publication:	Pramana
Publisher:	Indian Academy of Sciences
Additional Information:	Copyright of this article belongs to Indian Academy of Sciences.
Keywords:	Inductive inference;maximum entropy principle;prior distribution.
Department/Centre:	Division of Physical & Mathematical Sciences > Physics
Date Deposited:	27 Jan 2010 11:59
Last Modified:	19 Sep 2010 05:40
URI:	http://eprints.iisc.ac.in/id/eprint/22158

Actions (login required)

View Item