Abstract
A model of orthogonal greedy algorithm is proposed. This model allows one to consider computational errors and to study the stability of this algorithm with respect to errors in projections onto subspaces. A criterion for the convergence of orthogonal greedy expansion to the expanded element is given in terms of computational errors.
Similar content being viewed by others
References
J. H. Friedman and W. Stueuzle, “Projection Pursuit Regression,” J. Amer. Statist. Assoc. 76, 817 (1981).
L. K. Jones, “On a Conjecture of Huber Concerning the Convergence of PP-Regression,” Ann. Statist. 15, 880 (1987).
S. Mallat and Z. Zhang, “Matching Pursuit with Time-Frequency Dictionaries,” IEEE Trans. Signal Process. 41, 3397 (1993).
R. A. DeVore and V. N. Temlyakov, “Some Remarks on Greedy Algorithms,” Adv. Comput. Math. 5, 173 (1996).
V. N. Temlyakov, “Weak Greedy Algorithms,” Adv. Comput. Math. 12, 213 (2000).
V. V. Galatenko and E. D. Livshits, “Generalized Approximate Weak Greedy Algorithms,” Matem. Zametki 78(2), 186 (2005) [Math. Notes 78 (1–2), 170 (2005)].
R. Gribonval and M. Nielsen, “Approximate Weak Greedy Algorithms,” Adv. Comput. Math. 14, 361 (2001).
V. V. Galatenko, “Convergence of Weak Orthogonal Greedy Approximations,” in Proc. Voronezh Winter School “Modern Methods of the Theory of Functions and Related Problems,” (Voronezh, 2011), pp. 62–63.
V. V. Dubinin, Greedy Algorithms and Applications, Ph. D. Thesis. Univ. South Carolina, 1997.
S. B. Stechkin, “Absolute Convergence of Orthogonal Series,” Doklady Akad, Nauk SSSR 102, 37 (1955).
A. Barron, “Universal Approximation Bounds for Superposition of n Sigmoidal Functions,” IEEE Trans. Inf. Theory 39, 930 (1993).
Author information
Authors and Affiliations
Additional information
Original Russian Text © N.N. Fedotov. 2013. published in Vestnik Moskovskogo Universiteta, Matematika. Mekhanika, 2013. Vol. 68, No. 1, pp. 21–26.
About this article
Cite this article
Fedotov, N.N. Convergence of orthogonal greedy algorithm with errors in projectors. Moscow Univ. Math. Bull. 68, 37–41 (2013). https://doi.org/10.3103/S0027132213010075
Received:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0027132213010075