Stochastic Weakly Convex Optimization Beyond Lipschitz Continuity

This paper considers stochastic weakly convex optimization without the standard Lipschitz continuity assumption. Based on new adaptive regularization (stepsize) strategies, we show that a wide class of stochastic algorithms, including the stochastic subgradient method, preserve the 𝒪 ( 1 / √(K)) convergence rate with constant failure rate. Our analyses rest on rather weak assumptions: the Lipschitz parameter can be either bounded by a general growth function of x or locally estimated through independent random samples.