Exact Maximum-Entropy Estimation with Feynman Diagrams

Amitai Netser Zernik; Tomer M. Schlank; Ran J. Tessler

doi:10.1007/s10955-018-1960-x

Exact Maximum-Entropy Estimation with Feynman Diagrams

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

^*Corresponding author for this work

Einstein Institute of Mathematics

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

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 language	English
Pages (from-to)	731-747
Number of pages	17
Journal	Journal of Statistical Physics
Volume	170
Issue number	4
DOIs	https://doi.org/10.1007/s10955-018-1960-x
State	Published - 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

Access to Document

10.1007/s10955-018-1960-x

Cite this

@article{54dfc898c5404c2688f0235c57d62149,

title = "Exact Maximum-Entropy Estimation with Feynman Diagrams",

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.",

keywords = "Feynman calculus, Maximum entropy, Perturbative expansion, Weighted trees",

author = "\{Netser Zernik\}, Amitai and Schlank, \{Tomer M.\} and Tessler, \{Ran J.\}",

note = "Publisher Copyright: {\textcopyright} 2018, Springer Science+Business Media, LLC, part of Springer Nature.",

year = "2018",

month = feb,

day = "1",

doi = "10.1007/s10955-018-1960-x",

language = "אנגלית",

volume = "170",

pages = "731--747",

journal = "Journal of Statistical Physics",

issn = "0022-4715",

publisher = "Springer",

number = "4",

}

TY - JOUR

T1 - Exact Maximum-Entropy Estimation with Feynman Diagrams

AU - Netser Zernik, Amitai

AU - Schlank, Tomer M.

AU - Tessler, Ran J.

PY - 2018/2/1

Y1 - 2018/2/1

N2 - 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.

AB - 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.

KW - Feynman calculus

KW - Maximum entropy

KW - Perturbative expansion

KW - Weighted trees

UR - https://www.scopus.com/pages/publications/85040916111

U2 - 10.1007/s10955-018-1960-x

DO - 10.1007/s10955-018-1960-x

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85040916111

SN - 0022-4715

VL - 170

SP - 731

EP - 747

JO - Journal of Statistical Physics

JF - Journal of Statistical Physics

IS - 4

ER -

Exact Maximum-Entropy Estimation with Feynman Diagrams

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this