Neural Networks With Dense Weights Are Not Universal Approximators

Documenti analoghi

• Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
  di: Rauchwerger, Levi, et al.
  Pubblicazione: (2024)
• A Note on Graphon-Signal Analysis of Graph Neural Networks
  di: Rauchwerger, Levi, et al.
  Pubblicazione: (2025)
• Survey on Generalization Theory for Graph Neural Networks
  di: Vasileiou, Antonis, et al.
  Pubblicazione: (2025)
• A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
  di: Amran, Ofek, et al.
  Pubblicazione: (2026)
• Higher-Order Graphon Neural Networks: Approximation and Cut Distance
  di: Herbst, Daniel, et al.
  Pubblicazione: (2025)