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.
Similar content being viewed by others
References
Bracewell R N and Roberts J A 1954Aust. J. Phys. 7 615
Jaynes E T 1957Phys. Rev. 106 620;108 171
Shore J E and Johnson R 1980IEEE Trans. Inf. Theory 26 26 (SJ)
Shore J E and Johnson R 1983IEEE Trans. Inf. Theory 29 943
Tikochinsky Y, Tishby N Z and Levine R D 1984Phys. Rev. Lett. 52 1357 (TTL)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Karbelkar, S.N. On the axiomatic approach to the maximum entropy principle of inference. Pramana - J Phys 26, 301–310 (1986). https://doi.org/10.1007/BF02875589
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02875589