← Search

Marie-Charlotte Brandenburg

2 accepted papers

2025

Decomposition Polyhedra of Piecewise Linear Functions

ICLR 2025spotlight

In this paper we contribute to the frequently studied question of how to decompose a continuous piecewise linear (CPWL) function into a difference of two convex CPWL functions. Every CPWL function has infinitely many such decompositions, but for applications in optimization and neural network theory…

Cited by 4SourcePDFScholar
2025

How to Learn a Star: Binary Classification with Starshaped Polyhedral Sets

NeurIPS 2025poster

We consider binary classification restricted to a class of continuous piecewise linear functions whose decision boundaries are (possibly nonconvex) starshaped polyhedral sets, supported on a fixed polyhedral simplicial fan. We investigate the expressivity of these function classes and describe the c…

Cited by 0SourceScholar