Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

Documenti analoghi

• Does Flatness imply Generalization for Logistic Loss in Univariate Two-Layer ReLU Network?
  di: Qiao, Dan, et al.
  Pubblicazione: (2025)
• Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
  di: Park, Junhyung, et al.
  Pubblicazione: (2024)
• Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
  di: Liang, Tongtong, et al.
  Pubblicazione: (2025)
• The Geometry of ReLU Networks through the ReLU Transition Graph
  di: Dhayalkar, Sahil Rajesh
  Pubblicazione: (2025)
• N-ReLU: Zero-Mean Stochastic Extension of ReLU
  di: Manik, Md Motaleb Hossen, et al.
  Pubblicazione: (2025)