For functions satisfying an (α,β) subgradient growth condition, the paper's variance-reduced randomized smoothing method reaches a (δ,ε)-Goldstein stationary point in Õ(d^{3/2}δ^{-1}ε^{-3}) function evaluations with high probability.
Faster gradient-free algorithms for nonsmooth nonconvex stochastic optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting Randomized Smoothing: Nonsmooth Nonconvex Optimization Beyond Global Lipschitz Continuity
For functions satisfying an (α,β) subgradient growth condition, the paper's variance-reduced randomized smoothing method reaches a (δ,ε)-Goldstein stationary point in Õ(d^{3/2}δ^{-1}ε^{-3}) function evaluations with high probability.