ML Anthology

On Iterative Algorithms with an Information Geometry Background

Imre Csiszár
ALT 2008 pp. 1
doi:10.1007/978-3-540-87987-9_1 /alt/2008/csiszar2008alt-iterative/

Abstract

Several extremum problems in Statistics and Artificial Intelligence, e.g., likelihood maximization, are often solved by iterative algorithms such as iterative scaling or the EM algorithm, admitting an intuitive “geometric” interpretatation as iterated projections in the sense of Kullback information divergence. Such iterative algorithms, including those using Bregman rather than Kullback divergences, will be surveyed. It will be hinted to that the celebrated belief propagation (or sum-product) algorithm may also admit a similar interpretation.

PDF ALT Semantic Scholar

Cite

Text

Csiszár. "On Iterative Algorithms with an Information Geometry Background." International Conference on Algorithmic Learning Theory, 2008. doi:10.1007/978-3-540-87987-9_1

Markdown

[Csiszár. "On Iterative Algorithms with an Information Geometry Background." International Conference on Algorithmic Learning Theory, 2008.](https://mlanthology.org/alt/2008/csiszar2008alt-iterative/) doi:10.1007/978-3-540-87987-9_1

BibTeX

@inproceedings{csiszar2008alt-iterative,
  title     = {{On Iterative Algorithms with an Information Geometry Background}},
  author    = {Csiszár, Imre},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2008},
  pages     = {1},
  doi       = {10.1007/978-3-540-87987-9_1},
  url       = {https://mlanthology.org/alt/2008/csiszar2008alt-iterative/}
}