Convergence and rate of convergence of some greedy algorithms in convex optimization
Machine Learning
2014-12-11 v1 Numerical Analysis
Abstract
The paper gives a systematic study of the approximate versions of three greedy-type algorithms that are widely used in convex optimization. By approximate version we mean the one where some of evaluations are made with an error. Importance of such versions of greedy-type algorithms in convex optimization and in approximation theory was emphasized in previous literature.
Keywords
Cite
@article{arxiv.1412.3297,
title = {Convergence and rate of convergence of some greedy algorithms in convex optimization},
author = {Vladimir Temlyakov},
journal= {arXiv preprint arXiv:1412.3297},
year = {2014}
}