Consistent inference of probabilities for reproducible experiments

Y. Tikochinsky*, N. Z. Tishby, R. D. Levine

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

92 Scopus citations

Abstract

The need for inducing a probability distribution from partial data and the complementary problem of the analysis of an observed distribution in terms of fewer relevant variables occur in many branches of physics. For reproducible experiments, consistency conditions which must be satisfied by any algorithm for inferring a discrete probability distribution with given averages are formulated. The only consistent algorithm is the one leading to the distribution of maximal entropy subject to the given constraints.

Original languageEnglish
Pages (from-to)1357-1360
Number of pages4
JournalPhysical Review Letters
Volume52
Issue number16
DOIs
StatePublished - 1984

Fingerprint

Dive into the research topics of 'Consistent inference of probabilities for reproducible experiments'. Together they form a unique fingerprint.

Cite this