AI RESEARCH
Adaptive Lipschitz-Free Conditional Gradient Methods for Stochastic Composite Nonconvex Optimization
arXiv CS.LG
•
ArXi:2603.06369v1 Announce Type: new We propose ALFCG (Adaptive Lipschitz-Free Conditional Gradient), the first \textit{adaptive} projection-free framework for stochastic composite nonconvex minimization that \textit{requires neither global smoothness constants nor line search}. Unlike prior conditional gradient methods that use openloop diminishing stepsizes, conservative Lipschitz constants, or costly backtracking, ALFCG maintains a self-normalized accumulator of historical iterate differences to estimate local smoothness and minimize a quadratic surrogate model at each step.