Generalized Maximum Entropy for Supervised Classification
The maximum entropy principle advocates to evaluate events’ probabilities using a distribution that maximizes entropy among those that satisfy certain expectations’ constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper e...
| Autores: | ; ; |
|---|---|
| Tipo de documento: | Artículo |
| Estado: | Published version |
| Fecha de publicación: | 2022 |
| País: | España |
| Institución: | Basque Center for Applied Mathematics (BCAM) |
| Repositorio: | BIRD. BCAM's Institutional Repository Data |
| OAI Identifier: | oai:bird.bcamath.org:20.500.11824/1455 |
| Acceso en línea: | http://hdl.handle.net/20.500.11824/1455 |
| Nivel de acceso: | Acceso abierto |
| Palabra clave: | Supervised classification minimax risk classifiers maximum entropy generalized entropy |
| _version_ | 1878732962116141056 |
|---|---|
| author | Mazuelas, S. |
| author2 | Shen, Y. Pérez, A. |
| author2_role | author author |
| author_browse | Mazuelas, S. Pérez, A. Shen, Y. |
| author_facet | Mazuelas, S. Shen, Y. Pérez, A. |
| author_role | author |
| collection | BIRD. BCAM's Institutional Repository Data |
| description | The maximum entropy principle advocates to evaluate events’ probabilities using a distribution that maximizes entropy among those that satisfy certain expectations’ constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper establishes a framework for supervised classification based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). We develop learning techniques that determine MRCs for general entropy functions and provide performance guarantees by means of convex optimization. In addition, we describe the relationship of the presented techniques with existing classification methods, and quantify MRCs performance in comparison with the proposed bounds and conventional methods. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | ES_4d5ca16b728ff6c562bf40ca2f3d4afe |
| institution | Basque Center for Applied Mathematics (BCAM) |
| instname_str | Basque Center for Applied Mathematics (BCAM) |
| network_acronym_str | ES |
| network_name_str | España |
| oai_identifier_str | oai:bird.bcamath.org:20.500.11824/1455 |
| publishDate | 2022 |
| publishDateSort | 2022 |
| reponame_str | BIRD. BCAM's Institutional Repository Data |
| spelling | Generalized Maximum Entropy for Supervised Classification Mazuelas, S. Shen, Y. Pérez, A. Supervised classification minimax risk classifiers maximum entropy generalized entropy The maximum entropy principle advocates to evaluate events’ probabilities using a distribution that maximizes entropy among those that satisfy certain expectations’ constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper establishes a framework for supervised classification based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). We develop learning techniques that determine MRCs for general entropy functions and provide performance guarantees by means of convex optimization. In addition, we describe the relationship of the presented techniques with existing classification methods, and quantify MRCs performance in comparison with the proposed bounds and conventional methods. RYC-2016-19383 http://hdl.handle.net/20.500.11824/1455 |
| spellingShingle | Generalized Maximum Entropy for Supervised Classification Mazuelas, S. Supervised classification minimax risk classifiers maximum entropy generalized entropy |
| status_str | publishedVersion |
| title | Generalized Maximum Entropy for Supervised Classification |
| title_full | Generalized Maximum Entropy for Supervised Classification |
| title_fullStr | Generalized Maximum Entropy for Supervised Classification |
| title_full_unstemmed | Generalized Maximum Entropy for Supervised Classification |
| title_short | Generalized Maximum Entropy for Supervised Classification |
| title_sort | Generalized Maximum Entropy for Supervised Classification |
| topic | Supervised classification minimax risk classifiers maximum entropy generalized entropy |
| topic_facet | Supervised classification minimax risk classifiers maximum entropy generalized entropy |
| url | http://hdl.handle.net/20.500.11824/1455 |