Abstract
We introduce a novel second-order optimization framework for minimizing so-called variable projection functionals. We demonstrate that the proposed framework is especially usefulfor the training of variable projection based kernel methods. In particular, the problem of efficiently training variable projection support vector machines (VP-SVMs) is considered. We show the effectiveness of the proposed training methodology in a real-world application, namely we demonstrate how second-order trust region algorithms can be used to train VPSVM models to recognize road surface abnormalities based on 1D signals obtained from a tire sensor.
Keywords
Publication details
- DOI
- 10.1109/icassp55912.2026.11463454
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Angino, A., Voigt, M., Krause, R., & Dózsa, T. (2026). Second-order optimization of variable projection SVM models and road abnormality detection. https://doi.org/10.1109/icassp55912.2026.11463454
MLA 9
Angino, Andrea, et al. "Second-order optimization of variable projection SVM models and road abnormality detection." https://doi.org/10.1109/icassp55912.2026.11463454.
Chicago (author–date)
Angino, Andrea, Matthias Voigt, Rolf Krause, and Tamás Dózsa. 2026. "Second-order optimization of variable projection SVM models and road abnormality detection." https://doi.org/10.1109/icassp55912.2026.11463454.
Harvard
Angino, A., Voigt, M., Krause, R. and Dózsa, T. (2026) 'Second-order optimization of variable projection SVM models and road abnormality detection', doi:10.1109/icassp55912.2026.11463454.
Vancouver
Angino A, Voigt M, Krause R, Dózsa T. Second-order optimization of variable projection SVM models and road abnormality detection. doi:10.1109/icassp55912.2026.11463454
IEEE
A. Angino, M. Voigt, R. Krause, and T. Dózsa, "Second-order optimization of variable projection SVM models and road abnormality detection," doi: 10.1109/icassp55912.2026.11463454.