Under smooth convex constraints, the Switching Gradient Method retains an O(epsilon^-2) iteration complexity, and new soft switching and optimistic discretization variants are proposed to improve its behavior.
Oracle complexity of single-loop sw itching sub- gradient methods for non-smooth weakly convex functional c onstrained optimization,
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
-
Optimization via First-Order Switching Methods: Skew-Symmetric Dynamics and Optimistic Discretization
Under smooth convex constraints, the Switching Gradient Method retains an O(epsilon^-2) iteration complexity, and new soft switching and optimistic discretization variants are proposed to improve its behavior.