Lower bounds for finding stationary points II: first-order methods

We establish lower bounds on the complexity of finding similar to-stationary points of smooth, non-convex high-dimensional functions using first-order methods. We prove that deterministic first-order methods, even applied to arbitrarily smooth functions, cannot achieve convergence rates in similar to better than similar to -8/5, which is within similar to-1/15 log 1 similar to of the best known rate for such methods. Moreover, for functions with Lipschitz first and second derivatives, we prove that no deterministic first-order method can achieve convergence rates better than similar to -12/7, while similar to -2 is a lower bound for functions with only Lipschitz gradient. For convex functions with Lipschitz gradient, accelerated gradient descent achieves a better rate, showing that finding stationary points is easier given convexity.