Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.01797 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916113063870464 |
|---|---|
| author | Cepeda, Valentina Gómez, Andrés Han, Shaoning |
| author_facet | Cepeda, Valentina Gómez, Andrés Han, Shaoning |
| contents | We consider the problem of learning support vector machines robust to uncertainty. It has been established in the literature that typical loss functions, including the hinge loss, are sensible to data perturbations and outliers, thus performing poorly in the setting considered. In contrast, using the 0-1 loss or a suitable non-convex approximation results in robust estimators, at the expense of large computational costs. In this paper we use mixed-integer optimization techniques to derive a new loss function that better approximates the 0-1 loss compared with existing alternatives, while preserving the convexity of the learning problem. In our computational results, we show that the proposed estimator is competitive with the standard SVMs with the hinge loss in outlier-free regimes and better in the presence of outliers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01797 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robust support vector machines via conic optimization Cepeda, Valentina Gómez, Andrés Han, Shaoning Machine Learning Optimization and Control Computation We consider the problem of learning support vector machines robust to uncertainty. It has been established in the literature that typical loss functions, including the hinge loss, are sensible to data perturbations and outliers, thus performing poorly in the setting considered. In contrast, using the 0-1 loss or a suitable non-convex approximation results in robust estimators, at the expense of large computational costs. In this paper we use mixed-integer optimization techniques to derive a new loss function that better approximates the 0-1 loss compared with existing alternatives, while preserving the convexity of the learning problem. In our computational results, we show that the proposed estimator is competitive with the standard SVMs with the hinge loss in outlier-free regimes and better in the presence of outliers. |
| title | Robust support vector machines via conic optimization |
| topic | Machine Learning Optimization and Control Computation |
| url | https://arxiv.org/abs/2402.01797 |