Convergence and rate of convergence of some greedy algorithms in convex optimization

12/10/2014

∙

by   Vladimir Temlyakov, et al.

∙

0

∙

share

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.