Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory

Abstract

We note that known methods achieving the optimal oracle complexity for first order convex optimization require quadratic memory, and ask whether this is necessary, and more broadly seek to characterize the minimax number of first order queries required to optimize a convex Lipschitz function subject to a memory constraint.

9 pages

References in corpus (1)

• Lower Bound for Randomized First Order Convex Optimization