Frank-Wolfe iterates for monotone variational inequalities converge asymptotically to the solution set under vanishing nonsummable step sizes, with the gap vanishing and unique convergence in the strongly monotone case.
https://arxiv.org/abs/2402.18514
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2verdicts
UNVERDICTED 2representative citing papers
Derives accessible O(κΦ ln(κΦ ||w*||/ε)) iteration bound for rPDHG on unique-optima LPs, with computable Φ, two-stage performance, and equivalence to stability and sharpness.
citing papers explorer
-
Convergence of the Frank-Wolfe Algorithm for Monotone Variational Inequalities
Frank-Wolfe iterates for monotone variational inequalities converge asymptotically to the solution set under vanishing nonsummable step sizes, with the gap vanishing and unique convergence in the strongly monotone case.
-
Accessible Complexity Bounds for Restarted PDHG on Linear Programs with a Unique Optimizer
Derives accessible O(κΦ ln(κΦ ||w*||/ε)) iteration bound for rPDHG on unique-optima LPs, with computable Φ, two-stage performance, and equivalence to stability and sharpness.