A new step size rule lets boosted stochastic Frank-Wolfe match ordinary stochastic Frank-Wolfe rates on nonconvex and quasar-convex problems and deliver faster empirical convergence on sparse logistic regression and quantum tomography.
Martínez-Rubio
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
-
Boosted Stochastic Frank-Wolfe for Constrained Nonconvex Optimization
A new step size rule lets boosted stochastic Frank-Wolfe match ordinary stochastic Frank-Wolfe rates on nonconvex and quasar-convex problems and deliver faster empirical convergence on sparse logistic regression and quantum tomography.