A Theory of Mean Field Approximation

Abstract

I present a theory of mean field approximation based on information ge(cid:173) ometry. This theory includes in a consistent way the naive mean field approximation, as well as the TAP approach and the linear response the(cid:173) orem in statistical physics, giving clear information-theoretic interpreta(cid:173) tions to them.

Cite

Text

Tanaka. "A Theory of Mean Field Approximation." Neural Information Processing Systems, 1998.

Markdown

[Tanaka. "A Theory of Mean Field Approximation." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/tanaka1998neurips-theory/)

BibTeX

@inproceedings{tanaka1998neurips-theory,
  title     = {{A Theory of Mean Field Approximation}},
  author    = {Tanaka, Toshiyuki},
  booktitle = {Neural Information Processing Systems},
  year      = {1998},
  pages     = {351-360},
  url       = {https://mlanthology.org/neurips/1998/tanaka1998neurips-theory/}
}