Gradient Flows for L2 Support Vector Machine Training

Author: C. Bauckhage, H. Schneider, B. Wulff, R. Sifa
Journal: ICML
Year: 2022

Citation information

C. Bauckhage, H. Schneider, B. Wulff, R. Sifa,
ICML,
2022,
https://doi.org/10.48550/arXiv.2208.04365

We explore the merits of training of support vector machines for binary classification by means of solving systems of ordinary differential equations. We thus assume a continuous time perspective on a machine learning problem which may be of interest for implementations on (re)emerging hardware platforms such as analog- or quantum computers.