Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound

Documenti analoghi

• A Study of Condition Numbers for First-Order Optimization
  di: Guille-Escuret, Charles, et al.
  Pubblicazione: (2020)
• Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere?
  di: Meng, Si Yi, et al.
  Pubblicazione: (2025)
• On Linear Convergence of PI Consensus Algorithm under the Restricted Secant Inequality
  di: Chakrabarti, Kushal, et al.
  Pubblicazione: (2023)
• Provable non-accelerations of the heavy-ball method
  di: Goujaud, Baptiste, et al.
  Pubblicazione: (2023)
• Counter-examples in first-order optimization: a constructive approach
  di: Goujaud, Baptiste, et al.
  Pubblicazione: (2023)