Transient learning dynamics drive escape from sharp valleys in Stochastic Gradient Descent

Documenti analoghi

• On the different regimes of Stochastic Gradient Descent
  di: Sclocchi, Antonio, et al.
  Pubblicazione: (2023)
• Anti-Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances in Flat Directions
  di: Kühn, Marcel, et al.
  Pubblicazione: (2023)
• Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
  di: Angelini, Maria Chiara, et al.
  Pubblicazione: (2023)
• Growing Neural Networks: Dynamic Evolution through Gradient Descent
  di: Radhakrishnan, Anil, et al.
  Pubblicazione: (2025)
• Random Matrix Theory for Stochastic Gradient Descent
  di: Park, Chanju, et al.
  Pubblicazione: (2024)