ML Anthology

Maximum Entropy Principle in Non-Ordered Setting

Victor P. Maslov, Vladimir V. V'yugin
ALT 2004 pp. 221-233
doi:10.1007/978-3-540-30215-5_18 /alt/2004/maslov2004alt-maximum/

Abstract

We consider the Maximum Entropy principle for non-ordered data in a non-probabilistic setting. The main goal of this paper is to deduce asymptotic relations for the frequencies of the energy levels in a non-ordered sequence ω ^ N =[ ω _1,..., ω _ N ] from the assumption of maximality of the Kolmogorov complexity K( ω ^ N ) given a constraint $\sum\limits_{i=1}^N f(\omega_i)=N E$ , where E is a number and f is a numerical function.

PDF ALT Semantic Scholar

Cite

Text

Maslov and V'yugin. "Maximum Entropy Principle in Non-Ordered Setting." International Conference on Algorithmic Learning Theory, 2004. doi:10.1007/978-3-540-30215-5_18

Markdown

[Maslov and V'yugin. "Maximum Entropy Principle in Non-Ordered Setting." International Conference on Algorithmic Learning Theory, 2004.](https://mlanthology.org/alt/2004/maslov2004alt-maximum/) doi:10.1007/978-3-540-30215-5_18

BibTeX

@inproceedings{maslov2004alt-maximum,
  title     = {{Maximum Entropy Principle in Non-Ordered Setting}},
  author    = {Maslov, Victor P. and V'yugin, Vladimir V.},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2004},
  pages     = {221-233},
  doi       = {10.1007/978-3-540-30215-5_18},
  url       = {https://mlanthology.org/alt/2004/maslov2004alt-maximum/}
}