- News
- Subject and Goals
- Council and Annual Reports
- Contacts and Working Groups
- Lectures and Presentations
- Conferences and Seminars
- Publications
- Application Demos
- International Travels
- Visitors
- Past Events
- E-Synergy Login
SEARCH
MEMBERS OF RESEARCH CENTER
Research Centre
Data - Algorithms - Decision Making
Data - Algorithms - Decision Making
Established in 2005 under support of MŠMT ČR (project 1M0572)
Publications
Comparison of two methods for approximation of probability distributions with prescribed marginals
Typ:
Jornal article
Authors:
Perez A., Studený M.
Name of journal:
Kybernetika
Year:
2007
Number:
5 (2007)
Pages:
591-618
ISSN:
0023-5954
Keywords:
marginal problem, relative entropy, dependence structure sim
Anotation:
Let P be a discrete multidimensional distribution which is only partially specified by the requirement it has prescribed marginals. The paper deals with the problem of approximating P on the basis of those given marginals. Two methods for the approximation are compared, provided that the quality of an approximation is measured by relative entropy of P with respect the approximation.