Abstract
We find a class V of sequences such that the condition τ∉V is necessary and sufficient for convergence of weak greedy algorithm with weakness sequence τ for each f and all Hilbert spaces H and dictionaries D. We denote by V the class of sequences x={x k k=1 ∞, x k ≥0, k=1,2,..., with the following property: there exists a sequence 0=q 0<q 1<⋅⋅⋅ such that ∑ s=1 ∞2s/Δq s )<∞ and ∑ s=1 ∞2−s∑ k=1 q s x k 2<∞, where Δq s :=q s −q s−1.
Similar content being viewed by others
References
L. Jones, On a conjecture of Huber concerning the convergence of projection pursuit regression, Ann. Statist. 15 (1987) 880-882.
E.D. Livshitz and V.N. Temlyakov, On convergence of Weak Greedy Algorithms, IMI-Preprint No. 13 (2000) 1-9.
L. Rejtö and G.G. Walter, Remarks on projection pursuit regression and density estimation, Stochastic Anal. Appl. 10 (1992) 213-222.
V.N. Temlyakov, Weak Greedy Algorithms, Adv. Comput. Math. 12 (2000) 213-227.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Temlyakov, V. A Criterion for Convergence of Weak Greedy Algorithms. Advances in Computational Mathematics 17, 269–280 (2002). https://doi.org/10.1023/A:1016061804993
Issue Date:
DOI: https://doi.org/10.1023/A:1016061804993