One inexact gradient descent with momentum framework yields global and local convergence with PLK rates for extragradient, sharpness-aware minimization, and inexact proximal point methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convergence of First-Order Algorithms with Momentum from the Perspective of an Inexact Gradient Descent Method
One inexact gradient descent with momentum framework yields global and local convergence with PLK rates for extragradient, sharpness-aware minimization, and inexact proximal point methods.