Shortening step sizes by a factor of 1/(1+δ) improves the worst-case and practical robustness of long-step and accelerated first-order methods under relative gradient inexactness, with FGM emerging as empirically robust.
Acceleration by st epsize hedging: Silver stepsize schedule for smooth convex optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Empirical and computer-aided robustness analysis of long-step and accelerated methods in smooth convex optimization
Shortening step sizes by a factor of 1/(1+δ) improves the worst-case and practical robustness of long-step and accelerated first-order methods under relative gradient inexactness, with FGM emerging as empirically robust.