Heuristic approaches for support vector machines with the ramp loss
Recently, Support Vector Machines with the ramp loss (RLM) have attracted attention from the computational point of view. In this technical note, we propose two heuristics, the first one based on solving the continuous relaxation of a Mixed Integer Nonlinear formulation of the RLM and the second one...
| Authors: | ; ; |
|---|---|
| Format: | Article |
| Status: | Submitted version |
| Publication date: | 2014 |
| Country: | España |
| Institution: | Universidad de Sevilla (US) |
| Repository: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/44819 |
| Online Access: | http://hdl.handle.net/11441/44819 https://doi.org/10.1007/s11590-013-0630-9 |
| Access Level: | Open access |
| Keyword: | Support vector machines Ramp loss Mixed integer nonlinear programming Heuristics |
| _version_ | 1878740188907175936 |
|---|---|
| author | Carrizosa Priego, Emilio José |
| author2 | Nogales Gómez, Amaya Romero Morales, María Dolores |
| author2_role | author author |
| author_browse | Carrizosa Priego, Emilio José Nogales Gómez, Amaya Romero Morales, María Dolores |
| author_facet | Carrizosa Priego, Emilio José Nogales Gómez, Amaya Romero Morales, María Dolores |
| author_role | author |
| collection | idUS. Depósito de Investigación de la Universidad de Sevilla |
| description | Recently, Support Vector Machines with the ramp loss (RLM) have attracted attention from the computational point of view. In this technical note, we propose two heuristics, the first one based on solving the continuous relaxation of a Mixed Integer Nonlinear formulation of the RLM and the second one based on the training of an SVM classifier on a reduced dataset identified by an integer linear problem. Our computational results illustrate the ability of our heuristics to handle datasets of much larger size than those previously addressed in the literature. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | ES_cec53bc7dcd5caa7bec6cd5cf02a480a |
| institution | Universidad de Sevilla (US) |
| instname_str | Universidad de Sevilla (US) |
| network_acronym_str | ES |
| network_name_str | España |
| oai_identifier_str | oai:idus.us.es:11441/44819 |
| publishDate | 2014 |
| publishDateSort | 2014 |
| publisher | Springer |
| publisherStr | Springer |
| reponame_str | idUS. Depósito de Investigación de la Universidad de Sevilla |
| spelling | Heuristic approaches for support vector machines with the ramp loss Carrizosa Priego, Emilio José Nogales Gómez, Amaya Romero Morales, María Dolores Support vector machines Ramp loss Mixed integer nonlinear programming Heuristics Recently, Support Vector Machines with the ramp loss (RLM) have attracted attention from the computational point of view. In this technical note, we propose two heuristics, the first one based on solving the continuous relaxation of a Mixed Integer Nonlinear formulation of the RLM and the second one based on the training of an SVM classifier on a reduced dataset identified by an integer linear problem. Our computational results illustrate the ability of our heuristics to handle datasets of much larger size than those previously addressed in the literature. Ministerio de Economía y Competitividad Junta de Andalucía European Regional Development Funds Springer http://hdl.handle.net/11441/44819 https://doi.org/10.1007/s11590-013-0630-9 |
| spellingShingle | Heuristic approaches for support vector machines with the ramp loss Carrizosa Priego, Emilio José Support vector machines Ramp loss Mixed integer nonlinear programming Heuristics |
| status_str | submittedVersion |
| title | Heuristic approaches for support vector machines with the ramp loss |
| title_full | Heuristic approaches for support vector machines with the ramp loss |
| title_fullStr | Heuristic approaches for support vector machines with the ramp loss |
| title_full_unstemmed | Heuristic approaches for support vector machines with the ramp loss |
| title_short | Heuristic approaches for support vector machines with the ramp loss |
| title_sort | Heuristic approaches for support vector machines with the ramp loss |
| topic | Support vector machines Ramp loss Mixed integer nonlinear programming Heuristics |
| topic_facet | Support vector machines Ramp loss Mixed integer nonlinear programming Heuristics |
| url | http://hdl.handle.net/11441/44819 https://doi.org/10.1007/s11590-013-0630-9 |