Exact worst-case convergence rates of gradient descent: a complete analysis for all constant stepsizes over nonconvex and convex functions

Documenti analoghi

• Improved convergence rates for the Difference-of-Convex algorithm
  di: Rotaru, Teodor, et al.
  Pubblicazione: (2024)
• Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent
  di: Rotaru, Teodor, et al.
  Pubblicazione: (2025)
• Tight Convergence Rates in Gradient Mapping for the Difference-of-Convex Algorithm
  di: Rotaru, Teodor, et al.
  Pubblicazione: (2025)
• Worst-case convergence analysis of relatively inexact gradient descent on smooth convex functions
  di: Vernimmen, Pierre, et al.
  Pubblicazione: (2025)
• Analytic analysis of the worst-case complexity of the gradient method with exact line search and the Polyak stepsize
  di: Huang, Ya-Kui, et al.
  Pubblicazione: (2024)