Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory
Machine Learning
2019-07-02 v1 Optimization and Control
Machine Learning
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.
Cite
@article{arxiv.1907.00762,
title = {Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory},
author = {Blake Woodworth and Nathan Srebro},
journal= {arXiv preprint arXiv:1907.00762},
year = {2019}
}
Comments
9 pages