Tverberg's theorem and multi-class support vector machines

arXiv:2404.16724v1 Announce Type: new
Abstract: We show how, using linear-algebraic tools developed to prove Tverberg's theorem in combinatorial geometry, we can design new models of multi-class support vector machines (SVMs). These supervised learning protocols require fewer conditions to classify sets of points, and can be computed using existing binary SVM algorithms in higher-dimensional spaces, including soft-margin SVM algorithms. We describe how the theoretical guarantees of standard support vector machines transfer to these new classes of multi-class support vector machines. We …

abstract algorithms arxiv binary class cs.lg design geometry linear machines prove show supervised learning support support vector machines svm theorem tools type vector