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 originale | Anglais |
|---|---|
| Numéro d'article | 012018 |
| journal | Journal of Physics: Conference Series |
| Volume | 638 |
| Numéro de publication | 1 |
| Les DOIs | |
| état | Publié - 3 sept. 2015 |
| Evénement | 8th 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
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver