Paper ID: 2406.13888

Open Problem: Anytime Convergence Rate of Gradient Descent

Guy Kornowski, Ohad Shamir

Recent results show that vanilla gradient descent can be accelerated for smooth convex objectives, merely by changing the stepsize sequence. We show that this can lead to surprisingly large errors indefinitely, and therefore ask: Is there any stepsize schedule for gradient descent that accelerates the classic $\mathcal{O}(1/T)$ convergence rate, at \emph{any} stopping time $T$?

Submitted: Jun 19, 2024