A recursive sliding algorithm gives separate oracle complexity bounds for f, g, and bilinear products in Hölder-smooth minimax problems, interpolating from nonsmooth to smooth rates.
Forty-second International Conference on Machine Learning , year =
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
-
Sliding Methods for H\"older-Smooth Convex--Concave Minimax Optimization with Bilinear Coupling
A recursive sliding algorithm gives separate oracle complexity bounds for f, g, and bilinear products in Hölder-smooth minimax problems, interpolating from nonsmooth to smooth rates.