ML Anthology

Learning with Maximum-Entropy Distributions

Yishay Mansour, Mariano Schain
MLJ 2001 pp. 123-145
doi:10.1023/A:1010950718922 /mlj/2001/mansour2001mlj-learning/

Abstract

We are interested in distributions which are derived as a maximum entropy distribution from a given set of constraints. More specifically, we are interested in the case where the constraints are the expectation of individual and pairs of attributes. For such a given maximum entropy distribution (with some technical restrictions) we develop an efficient learning algorithm for read-once DNF. We extend our results to monotone read-k DNF following the techniques of (Hancock & Mansour, 1991).

PDF MLJ Semantic Scholar

Cite

Text

Mansour and Schain. "Learning with Maximum-Entropy Distributions." Machine Learning, 2001. doi:10.1023/A:1010950718922

Markdown

[Mansour and Schain. "Learning with Maximum-Entropy Distributions." Machine Learning, 2001.](https://mlanthology.org/mlj/2001/mansour2001mlj-learning/) doi:10.1023/A:1010950718922

BibTeX

@article{mansour2001mlj-learning,
  title     = {{Learning with Maximum-Entropy Distributions}},
  author    = {Mansour, Yishay and Schain, Mariano},
  journal   = {Machine Learning},
  year      = {2001},
  pages     = {123-145},
  doi       = {10.1023/A:1010950718922},
  volume    = {45},
  url       = {https://mlanthology.org/mlj/2001/mansour2001mlj-learning/}
}