Gradient-FreeMethodsforNonconvexNonsmooth StochasticCompositionalOptimization
–Neural Information Processing Systems
Most of the existing work [2, 5, 6, 7, 8] for nonconvex SCO problem is based on the assumption that both functionsf()andg()are smooth.
Neural Information Processing Systems
Feb-13-2026, 01:55:07 GMT