An interesting link between linear feasibility, linear programming, support vector machine and convex hull.

Adrien Chan-Hon-Tong (1)

1 ONERA, Université Paris Saclay (COmUE) [Palaiseau]

This short paper presents an algorithm based on simple projections and linear feasibility queries which solves both linear programming, and, support vector machine. In addition, this algorithm is strongly polynomial on families of instances of linear program and support vector machine, characterized by similar convex hull properties. Thus, this algorithm could be interesting as a link between all these four notions: linear feasibility, linear programming, support vector machine and convex hull.

Mots clés: Linear programming; Strongly polynomial

Domaines: Recherche opérationnelle [math.OC]

Adrien Chan-Hon-Tong. An interesting link between linear feasibility, linear programming, support vector machine and convex hull.. 2019. ⟨hal-00722920v14⟩