Log-gamma distribution optimisation via maximum likelihood for ordered probability estimates

Áreas de investigación:

• Methodology - Machine learning

Año:

2014

Tipo de publicación:

Artículo en conferencia

Autores:

• Pérez-Ortiz, María
• Gutiérrez, Pedro Antonio
• Hervás-Martínez, César

Volumen:

8480

Título del libro:

9th International Conference on Hybrid Artificial Intelligence Systems (HAIS2014)

Serie:

Lecture Notes in Computer Science (LNCS)

Páginas:

454-465

Organización:

Salamanca (Spain)

Mes:

11th-13th June

ISBN:

978-3-319-07616-4

ISSN:

0302-9743

BibTex:

@conference{LGDOviaMLHAIS, author = "Mar{\'i}a P{\'e}rez-Ortiz and Pedro Antonio Guti{\'e}rrez and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "Ordinal regression considers classification problems where there exist a natural ordering between the categories. In this learning setting, thresholds models are one of the most used and successful techniques. These models are based on the idea of projecting the patterns to a line, which is thereafter divided into intervals using a set of biases or thresholds. This paper proposes a general likelihood-based optimisation framework to better fit probability distributions for ordered categories. To do so, a specific probability distribution (log-gamma) is used, which generalises three commonly used link functions (log-log, probit and complementary log-log). The experiments show that the methodology is not only useful to provide a probabilistic output of the classifier but also to improve the performance of threshold models when reformulating the prediction rule to take these probabilities into account.", booktitle = "9th International Conference on Hybrid Artificial Intelligence Systems (HAIS2014)", doi = "10.1007/978-3-319-07617-1_40", isbn = "978-3-319-07616-4", issn = "0302-9743", month = "11th-13th June", organization = "Salamanca (Spain)", pages = "454--465", publisher = "Springer", series = "Lecture Notes in Computer Science (LNCS)", title = "{L}og-gamma distribution optimisation via maximum likelihood for ordered probability estimates", url = "http://dx.doi.org/10.1007/978-3-319-07617-1_40", volume = "8480", year = "2014", }

Abstract:

Ordinal regression considers classification problems where there exist a natural ordering between the categories. In this learning setting, thresholds models are one of the most used and successful techniques. These models are based on the idea of projecting the patterns to a line, which is thereafter divided into intervals using a set of biases or thresholds. This paper proposes a general likelihood-based optimisation framework to better fit probability distributions for ordered categories. To do so, a specific probability distribution (log-gamma) is used, which generalises three commonly used link functions (log-log, probit and complementary log-log). The experiments show that the methodology is not only useful to provide a probabilistic output of the classifier but also to improve the performance of threshold models when reformulating the prediction rule to take these probabilities into account.