Open Problem: Anytime Convergence Rate of Gradient Descent
Optimization and Control
2024-06-21 v1 Machine Learning
Abstract
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 convergence rate, at \emph{any} stopping time ?
Keywords
Cite
@article{arxiv.2406.13888,
title = {Open Problem: Anytime Convergence Rate of Gradient Descent},
author = {Guy Kornowski and Ohad Shamir},
journal= {arXiv preprint arXiv:2406.13888},
year = {2024}
}
Comments
COLT 2024 open problem; 5 pages