# The Complexity of Finding Stationary Points with Stochastic Gradient Descent

4 Oct 2019Yoel DroriOhad Shamir

We study the iteration complexity of stochastic gradient descent (SGD) for minimizing the gradient norm of smooth, possibly nonconvex functions. We provide several results, implying that the classical $\mathcal{O}(\epsilon^{-4})$ upper bound (for making the average gradient norm less than $\epsilon$) cannot be improved upon, unless a combination of additional assumptions is made... (read more)

PDF Abstract

# Code Add Remove

No code implementations yet. Submit your code now