The exact information-based complexity of smooth convex minimization
Optimization and Control
2016-06-07 v1
Abstract
We obtain a new lower bound on the information-based complexity of first-order minimization of smooth and convex functions. We show that the bound matches the worst-case performance of the recently introduced Optimized Gradient Method, thereby establishing that the bound is tight and can be realized by an efficient algorithm. The proof is based on a novel construction technique of smooth and convex functions.
Cite
@article{arxiv.1606.01424,
title = {The exact information-based complexity of smooth convex minimization},
author = {Yoel Drori},
journal= {arXiv preprint arXiv:1606.01424},
year = {2016}
}