Convergence and rate of convergence of some greedy algorithms in convex optimization
arXiv:1412.3297v16 citations
Originality Synthesis-oriented
AI Analysis
This work provides theoretical analysis for incremental improvements in convex optimization algorithms, relevant to researchers in optimization and approximation theory.
The paper systematically studies approximate versions of three greedy algorithms in convex optimization, where evaluations are made with errors, addressing their convergence and rate of convergence.
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.