AdCGS combines conditional gradient sliding with adaptive local-Lipschitz stepsizes to achieve accelerated projection-free, line-search-free convergence for convex and strongly convex objectives.
Then, for any j∈{ 1,...,k }, it holds that ζk≤ Λk 0 @ 1−λj Λj ζj−1 + kX i=j νi Λi 1 A
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
-
Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
AdCGS combines conditional gradient sliding with adaptive local-Lipschitz stepsizes to achieve accelerated projection-free, line-search-free convergence for convex and strongly convex objectives.