Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Froese, Vincent"'
Neural networks with ReLU activation play a key role in modern machine learning. In view of safety-critical applications, the verification of trained networks is of great importance and necessitates a thorough understanding of essential properties of
Externí odkaz:
http://arxiv.org/abs/2405.19805
Autor:
Pawlowski, Simeon, Froese, Vincent
We study Voronoi games on temporal graphs as introduced by Boehmer et al. (IJCAI 2021) where two players each select a vertex in a temporal graph with the goal of reaching the other vertices earlier than the other player. In this work, we consider th
Externí odkaz:
http://arxiv.org/abs/2402.04696
Autor:
Froese, Vincent, Hertrich, Christoph
We study the parameterized complexity of training two-layer neural networks with respect to the dimension of the input data and the number of hidden neurons, considering ReLU and linear threshold activation functions. Albeit the computational complex
Externí odkaz:
http://arxiv.org/abs/2303.17045
Autor:
Froese, Vincent, Renken, Malte
A graph with vertex set $\{1,\ldots,n\}$ is terrain-like if, for any edge pair $\{a,c\},\{b,d\}$ with $a
Externí odkaz:
http://arxiv.org/abs/2210.16281
Data reduction rules are an established method in the algorithmic toolbox for tackling computationally challenging problems. A data reduction rule is a polynomial-time algorithm that, given a problem instance as input, outputs an equivalent, typicall
Externí odkaz:
http://arxiv.org/abs/2206.14698
We study the network untangling problem introduced by Rozenshtein, Tatti, and Gionis [DMKD 2021], which is a variant of Vertex Cover on temporal graphs -- graphs whose edge set changes over discrete time steps. They introduce two problem variants. Th
Externí odkaz:
http://arxiv.org/abs/2204.02668
The classic Cluster Editing problem (also known as Correlation Clustering) asks to transform a given graph into a disjoint union of cliques (clusters) by a small number of edge modifications. When applied to vertex-colored graphs (the colors represen
Externí odkaz:
http://arxiv.org/abs/2112.03183
Publikováno v:
Journal of Artificial Intelligence Research 74 (2022): 1775-1790
Understanding the computational complexity of training simple neural networks with rectified linear units (ReLUs) has recently been a subject of intensive research. Closing gaps and complementing results from the literature, we present several result
Externí odkaz:
http://arxiv.org/abs/2105.08675
In the simplest game-theoretic formulation of Schelling's model of segregation on graphs, agents of two different types each select their own vertex in a given graph so as to maximize the fraction of agents of their type in their occupied neighborhoo
Externí odkaz:
http://arxiv.org/abs/2105.06561
Autor:
Boehmer, Niclas, Froese, Vincent, Henkel, Julia, Lasars, Yvonne, Niedermeier, Rolf, Renken, Malte
To address the dynamic nature of real-world networks, we generalize competitive diffusion games and Voronoi games from static to temporal graphs, where edges may appear or disappear over time. This establishes a new direction of studies in the area o
Externí odkaz:
http://arxiv.org/abs/2105.05987