activity
20202026
most citedTraining Fully Connected Neural Networks is -Complete

7 citations · 10 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CG2026

Bowties and Hourglasses: Intersections of Double-Wedges (or Stabbing and Avoiding Line Segments)

Daniel Bertschinger, Henry Förster, Fabian Klute +3

We study the common intersection of arrangements of double-wedges. We consider arrangements where double-wedges may be either bowties (which do not contain a vertical line) or hour…

cs.CG2023★ 1 cited

The Complexity of Recognizing Geometric Hypergraphs

Daniel Bertschinger, Nicolas El Maalouly, Linda Kleist +2

As set systems, hypergraphs are omnipresent and have various representations ranging from Euler and Venn diagrams to contact representations. In a geometric representation of a hyp…

cs.CG2022

Well-Separation and Hyperplane Transversals in High Dimensions

Helena Bergold, Daniel Bertschinger, Nicolas Grelier +2

A family of point sets in dimensions is well-separated if the convex hulls of any two disjoint subfamilies can be separated by a hyperplane. Well-separation is a strong ass…

cs.CC2022★ 7 cited

Training Fully Connected Neural Networks is -Complete

Daniel Bertschinger, Christoph Hertrich, Paul Jungeblut +2

We consider the problem of finding weights and biases for a two-layer fully connected neural network to fit a given set of data points as well as possible, also known as EmpiricalR…

cs.CG2021★ 2 cited

Topological Art in Simple Galleries

Daniel Bertschinger, Nicolas El Maalouly, Tillmann Miltzow +2

Let be a simple polygon, then the art gallery problem is looking for a minimum set of points (guards) that can see every point in . We say two points can see each…

cs.CG2021

Tukey Depth Histograms

Daniel Bertschinger, Jonas Passweg, Patrick Schnider

The Tukey depth of a flat with respect to a point set is a concept that appears in many areas of discrete and computational geometry. In particular, the study of centerpoints, cent…