, Volume 26, Issue 4, pp 301–310 | Cite as

On the axiomatic approach to the maximum entropy principle of inference

  • S N Karbelkar
Statistical Physics


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 ∝ dxp(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.


Inductive inference maximum entropy principle prior distribution 


02.50 03.65 05.20 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bracewell R N and Roberts J A 1954Aust. J. Phys. 7 615ADSGoogle Scholar
  2. Jaynes E T 1957Phys. Rev. 106 620;108 171CrossRefADSMathSciNetGoogle Scholar
  3. Shore J E and Johnson R 1980IEEE Trans. Inf. Theory 26 26 (SJ)MATHCrossRefADSMathSciNetGoogle Scholar
  4. Shore J E and Johnson R 1983IEEE Trans. Inf. Theory 29 943CrossRefMathSciNetGoogle Scholar
  5. Tikochinsky Y, Tishby N Z and Levine R D 1984Phys. Rev. Lett. 52 1357 (TTL)CrossRefADSGoogle Scholar

Copyright information

© Indian Academy of Sciences 1993

Authors and Affiliations

  • S N Karbelkar
    • 1
  1. 1.Joint Astronomy Program, Physics DepartmentIndian Institute of ScienceBangaloreIndia

Personalised recommendations