Bounding the Worst-class Error: A Boosting Approach
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918095892774912 |
|---|---|
| author | Saito, Yuya Matsuo, Shinnosuke Uchida, Seiichi Suehiro, Daiki |
| author_facet | Saito, Yuya Matsuo, Shinnosuke Uchida, Seiichi Suehiro, Daiki |
| contents | This paper tackles the problem of the worst-class error rate, instead of the standard error rate averaged over all classes. For example, a three-class classification task with class-wise error rates of 10%, 10%, and 40% has a worst-class error rate of 40%, whereas the average is 20% under the class-balanced condition. The worst-class error is important in many applications. For example, in a medical image classification task, it would not be acceptable for the malignant tumor class to have a 40% error rate, while the benign and healthy classes have a 10% error rates. To avoid overfitting in worst-class error minimization using Deep Neural Networks (DNNs), we design a problem formulation for bounding the worst-class error instead of achieving zero worst-class error. Moreover, to correctly bound the worst-class error, we propose a boosting approach which ensembles DNNs. We give training and generalization worst-class-error bound. Experimental results show that the algorithm lowers worst-class test error rates while avoiding overfitting to the training set. This code is available at https://github.com/saito-yuya/Bounding-the-Worst-class-error-A-Boosting-Approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_14890 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Bounding the Worst-class Error: A Boosting Approach Saito, Yuya Matsuo, Shinnosuke Uchida, Seiichi Suehiro, Daiki Machine Learning Artificial Intelligence This paper tackles the problem of the worst-class error rate, instead of the standard error rate averaged over all classes. For example, a three-class classification task with class-wise error rates of 10%, 10%, and 40% has a worst-class error rate of 40%, whereas the average is 20% under the class-balanced condition. The worst-class error is important in many applications. For example, in a medical image classification task, it would not be acceptable for the malignant tumor class to have a 40% error rate, while the benign and healthy classes have a 10% error rates. To avoid overfitting in worst-class error minimization using Deep Neural Networks (DNNs), we design a problem formulation for bounding the worst-class error instead of achieving zero worst-class error. Moreover, to correctly bound the worst-class error, we propose a boosting approach which ensembles DNNs. We give training and generalization worst-class-error bound. Experimental results show that the algorithm lowers worst-class test error rates while avoiding overfitting to the training set. This code is available at https://github.com/saito-yuya/Bounding-the-Worst-class-error-A-Boosting-Approach. |
| title | Bounding the Worst-class Error: A Boosting Approach |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2310.14890 |