Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime

Documenti analoghi

• Improved geometric and recollision estimates for the invariance principle of the random Lorentz gas
  di: Matthies, Karsten, et al.
  Pubblicazione: (2025)
• The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram
  di: Chizat, Lénaïc
  Pubblicazione: (2025)
• A flow-type scaling limit for random growth with memory
  di: Dembo, Amir, et al.
  Pubblicazione: (2023)
• Semi-Quenched Invariance Principle for the Random Lorentz Gas -- Beyond the Boltzmann-Grad Limit
  di: Tóth, Bálint
  Pubblicazione: (2024)
• Normalization in Attention Dynamics
  di: Karagodin, Nikita, et al.
  Pubblicazione: (2025)