AI RESEARCH
Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle
arXiv CS.LG
•
ArXi:2605.08850v1 Announce Type: cross We design Local LMO - a new projection-free gradient-type method for constrained optimization. The key algorithmic idea is to replace the global linear minimization oracle over the constraint set used by Frank-Wolfe (FW) with a local linear minimization oracle over the intersection of the constraint set and a "small" ball centered at the current iterate.