Anchored GDA attains last-iterate O(1/t) convergence for the squared gradient norm in smooth convex-concave min-max optimization.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
An Improved Last-Iterate Convergence Rate for Anchored Gradient Descent Ascent
Anchored GDA attains last-iterate O(1/t) convergence for the squared gradient norm in smooth convex-concave min-max optimization.