Large margin classifier with graph-based adaptive regularization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911643027374080 |
|---|---|
| author | Hanriot, Vítor M. Salis, Turíbio T. Torres, Luiz C. B. Coelho, Frederico Braga, Antonio P. |
| author_facet | Hanriot, Vítor M. Salis, Turíbio T. Torres, Luiz C. B. Coelho, Frederico Braga, Antonio P. |
| contents | This paper introduces the use of per-class regularization hyperparameters in Gabriel graph-based binary classifiers. We demonstrate how the quality index used for regularization behaves both in the margin region and in the presence of outliers, and how incorporating this regularization flexibility can lead to solutions that effectively eliminate outliers while training the classifier. We also show how it can address class imbalance by generating higher and lower thresholds for the majority and minority classes, respectively. Thus, rather than having a single solution based on fixed thresholds, flexible thresholds expand the solution space and can be optimized through hyperparameter tuning algorithms. Friedman test shows that flexible thresholds are capable of improving Gabriel graph-based classifiers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02027 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Large margin classifier with graph-based adaptive regularization Hanriot, Vítor M. Salis, Turíbio T. Torres, Luiz C. B. Coelho, Frederico Braga, Antonio P. Machine Learning This paper introduces the use of per-class regularization hyperparameters in Gabriel graph-based binary classifiers. We demonstrate how the quality index used for regularization behaves both in the margin region and in the presence of outliers, and how incorporating this regularization flexibility can lead to solutions that effectively eliminate outliers while training the classifier. We also show how it can address class imbalance by generating higher and lower thresholds for the majority and minority classes, respectively. Thus, rather than having a single solution based on fixed thresholds, flexible thresholds expand the solution space and can be optimized through hyperparameter tuning algorithms. Friedman test shows that flexible thresholds are capable of improving Gabriel graph-based classifiers. |
| title | Large margin classifier with graph-based adaptive regularization |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.02027 |