Gradient Flows for L2 Support Vector Machine Training

Abstract

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.

Peer-reviewed and presented as part of the workshop on Continuous Time Methods for Machine Learning at the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, 2022