A Frank-Wolfe method that adapts both the smoothness constant and the triangle-scaling exponent achieves sublinear convergence and a tolerance-dependent linear rate, with a centralized distributed optimization application.
In: International Conference on Optimization and Applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Fully Adaptive Frank-Wolfe Algorithm for Relatively Smooth Problems and Its Application to Centralized Distributed Optimization
A Frank-Wolfe method that adapts both the smoothness constant and the triangle-scaling exponent achieves sublinear convergence and a tolerance-dependent linear rate, with a centralized distributed optimization application.