Passer à la navigation principale Passer à la recherche Passer au contenu principal

Learning probability distributions from smooth observables and the maximum entropy principle: Some remarks

  • Tokyo Institute of Technology

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

6 Citations (Scopus)

Résumé

The maximum entropy principle (MEP) is a very useful working hypothesis in a wide variety of inference problems, ranging from biological to engineering tasks. To better understand the reasons of the success of MEP, we propose a statistical-mechanical formulation to treat the space of probability distributions constrained by the measures of (experimental) observables. In this paper we first review the results of a detailed analysis of the simplest case of randomly chosen observables. In addition, we investigate by numerical and analytical means the case of smooth observables, which is of practical relevance. Our preliminary results are presented and discussed with respect to the efficiency of the MEP.

langue originaleAnglais
Numéro d'article012018
journalJournal of Physics: Conference Series
Volume638
Numéro de publication1
Les DOIs
étatPublié - 3 sept. 2015
Evénement8th International Conferences on Statistical Physics, Statphys-Kolkata 2014 - Kolkata, Inde
Durée: 1 déc. 2014 → 5 déc. 2014

Empreinte digitale

Examiner les sujets de recherche de « Learning probability distributions from smooth observables and the maximum entropy principle: Some remarks ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation