Auto-conditioned Frank-Wolfe methods use local Lipschitz estimators from first-order information to achieve convergence guarantees in convex and nonconvex settings without prior global smoothness knowledge.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Auto-Conditioned Frank-Wolfe Algorithms
Auto-conditioned Frank-Wolfe methods use local Lipschitz estimators from first-order information to achieve convergence guarantees in convex and nonconvex settings without prior global smoothness knowledge.