Training Instabilities Induce Flatness Bias in Gradient Descent

Documenti analoghi

• Can Stability be Detrimental? Better Generalization through Gradient Descent Instabilities
  di: Wang, Lawrence, et al.
  Pubblicazione: (2024)
• The Implicit Bias of Gradient Descent on Separable Multiclass Data
  di: Ravi, Hrithik, et al.
  Pubblicazione: (2024)
• The Implicit Bias of Gradient Descent on Separable Data
  di: Soudry, Daniel, et al.
  Pubblicazione: (2017)
• The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
  di: Li, Jichu, et al.
  Pubblicazione: (2026)
• Understanding Gradient Descent through the Training Jacobian
  di: Belrose, Nora, et al.
  Pubblicazione: (2024)