Application of the method of maximum entropy in the mean to classification problems

In this note we propose an application of the method of maximum entropy in the mean to solve a class of inverse problems comprising classification problems and feasibility problems appearing in optimization. Such problems may be thought of as linear inverse problems with convex constraints imposed on the solution as well as on the data. The method of maximum entropy in the mean proves to be a very useful tool to deal with this type of problems.

• Autores: Gzyl, Henryk; ter Horst, Enrique; Molina, Germán
• Tipo de recurso: Article of investigation
• Fecha de publicación: 2015
• Institución: Colegio de Estudios Superiores de Administración
• Repositorio: Repositorio CESA
• Idioma: eng
• OAI Identifier: oai:repository.cesa.edu.co:10726/5118
• Acceso en línea: http://hdl.handle.net/10726/5118; https://doi.org/10.1016/j.physa.2015.05.105
• Palabra clave: Maximum entropy in the mean; Classification problems; Credit scoring; Linear inverse problems
• License: Acceso Restringido