Escaping saddle points in zeroth-order optimization: the power of two-point estimators

Two-point zeroth order methods are important in many applications of zeroth-order optimization, such as robotics, wind farms, power systems, online optimization, and adversarial robustness to black-box attacks in deep neural networks, where the problem may be high-dimensional and/or time-varying. Most problems in these applications are nonconvex and contain saddle points. While existing works have shown that zeroth-order methods utilizing Omega(d) function valuations per iteration (with d denoting the problem dimension) can escape saddle points efficiently, it remains an open question if zeroth-order methods based on two-point estimators can escape saddle points. In this paper, we show that by adding an appropriate isotropic perturbation at each iteration, a zeroth-order algorithm based on 2m (for any 1 ≤ m ≤ d) function evaluations per iteration can not only find ε-second order stationary points polynomially fast, but do so using only tildeOleft(fracdmε2barpsiright) function evaluations, where barpsi ≥ tildeOmegaleft(√εright) is a parameter capturing the extent to which the function of interest exhibits the strict saddle property.