Neural network optimization strategies and the topography of the loss landscape

Documenti analoghi

• On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime
  di: Jiang, Shuai, et al.
  Pubblicazione: (2026)
• Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training
  di: Bolshim, Maxim, et al.
  Pubblicazione: (2026)
• Local properties of neural networks through the lens of layer-wise Hessians
  di: Bolshim, Maxim, et al.
  Pubblicazione: (2025)
• Data-induced multiscale losses and efficient multirate gradient descent schemes
  di: He, Juncai, et al.
  Pubblicazione: (2024)
• Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures
  di: Bolshim, Maxim, et al.
  Pubblicazione: (2026)