A direct Lyapunov argument establishes near-linear convergence of a more adaptive gradient descent method for convex functions satisfying fourth-order growth, bypassing an earlier intricate ravine-monitoring proof.
Big-step-little-step: Efficient gradient methods for objectives with multiple scales
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity
A direct Lyapunov argument establishes near-linear convergence of a more adaptive gradient descent method for convex functions satisfying fourth-order growth, bypassing an earlier intricate ravine-monitoring proof.