Exact Maximum-Entropy Estimation with Feynman Diagrams

Amitai Netser Zernik, Tomer M. Schlank, Ran J. Tessler*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

A longstanding open problem in statistics is finding an explicit expression for the probability measure which maximizes entropy with respect to given constraints. In this paper a solution to this problem is found, using perturbative Feynman calculus. The explicit expression is given as a sum over weighted trees.

Original languageEnglish
Pages (from-to)731-747
Number of pages17
JournalJournal of Statistical Physics
Volume170
Issue number4
DOIs
StatePublished - 1 Feb 2018

Bibliographical note

Publisher Copyright:
© 2018, Springer Science+Business Media, LLC, part of Springer Nature.

Keywords

  • Feynman calculus
  • Maximum entropy
  • Perturbative expansion
  • Weighted trees

Fingerprint

Dive into the research topics of 'Exact Maximum-Entropy Estimation with Feynman Diagrams'. Together they form a unique fingerprint.

Cite this