# Stochastic gradient descent for nonconvex functions

I am trying to optimize a nonconvex function of the form

$$f(x) = \sum_i g_i(x) - h_i(x)$$

where x is a vector of variables, and $g_i$ and $h_i$ are both convex. While I am aware that such a function can be optimized using a Concave Convex Procedure (CCCP) to a local minima, I am wondering if I can say something about a stochastic gradient method for this function (even guarantees of reaching a local minima will be fine.)

Does anyone have any advice or references?

-