A geometric alternative to Nesterov's accelerated gradient descent
Optimization and Control
2015-06-30 v1 Data Structures and Algorithms
Machine Learning
Numerical Analysis
Abstract
We propose a new method for unconstrained optimization of a smooth and strongly convex function, which attains the optimal rate of convergence of Nesterov's accelerated gradient descent. The new algorithm has a simple geometric interpretation, loosely inspired by the ellipsoid method. We provide some numerical evidence that the new method can be superior to Nesterov's accelerated gradient descent.
Cite
@article{arxiv.1506.08187,
title = {A geometric alternative to Nesterov's accelerated gradient descent},
author = {Sébastien Bubeck and Yin Tat Lee and Mohit Singh},
journal= {arXiv preprint arXiv:1506.08187},
year = {2015}
}