Training Neural Networks is NP-Hard in Fixed Dimension

Documenti analoghi

• ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation
  di: Hertrich, Christoph, et al.
  Pubblicazione: (2021)
• Parameterized Hardness of Zonotope Containment and Neural Network Verification
  di: Froese, Vincent, et al.
  Pubblicazione: (2025)
• Learning to Approximate Uniform Facility Location via Graph Neural Networks
  di: Qian, Chendi, et al.
  Pubblicazione: (2026)
• Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete
  di: Bertschinger, Daniel, et al.
  Pubblicazione: (2022)
• Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size
  di: Hertrich, Christoph, et al.
  Pubblicazione: (2020)