Lower- and upper-C² integrands: a structured class of functions for stochastic nonconvex optimization

We study nonconvex stochastic functions that admit a structured second-order representation, a generalization of lower- and upper-C² functions to normal integrands. Similarly to the deterministic case, lower-C² normal integrands are defined as the pointwise maxima over a compact random index set of functions that are twice-continuously differentiable in the decision variable with an integrable bounded … Read more

A line search proximal subgradient method for nonconvex stochastic optimization

This work introduces a proximal sample-average subgradient method for minimizing the sum of an expected cost, whose integrand is potentially nonsmooth and nonconvex, and a lower semicontinuous, prox-bounded function. We target the class of upper-$C^2$ integrands obeying a nonsmooth, localized variant of the descent lemma in the decision variable, a structural assumption that simultaneously covers … Read more