Abstract
We present a generalization of Temlyakov's weak greedy algorithm, and give a sufficient condition for norm convergence of the algorithm for an arbitrary dictionary in a Hilbert space. We provide two counter-examples to show that the condition cannot be relaxed for general dictionaries. For a class of dictionaries with more structure, we give a more relaxed necessary and sufficient condition for convergence of the algorithm. We also provide a detailed discussion of how a “real-world” implementation of the weak greedy algorithm, where one has to take into account floating point arithmetic and other types of finite precision errors, can be modeled by the new algorithm.
Similar content being viewed by others
References
F. Bergeaud, Représentations adaptatives d'images numériques, Matching Pursuit, Ph.D. thesis, Ecole Centrale Paris (1995).
F. Bergeaud and S. Mallat, Matching Pursuit: Adaptative representations of images and sounds, Comput. Appl. Math. 15(2) (1996).
A. Bultan, A four-parameter atomic decomposition of chirplets, IEEE Trans. Signal Process. 47(3) (1999) 731–745.
R.R. Coifman and Y. Meyer, Remarques sur l'analyse de Fourier à fenêtre, C. R. Acad. Sci. Paris Sér. A 312 (1991) 259–261.
R.R. Coifman, Y. Meyer, S.R. Quake and M.V. Wickerhauser, Signal processing and compression with wavelet packets, in: Progress in Wavelet Analysis and Applications, eds. Y.Meyer and S. Roques (1992).
G. Davis, S. Mallat and M. Avellaneda, Adaptive greedy approximations, Constr. Approx. 13 (1997) 57–98.
J.H. Friedman and W. Stuetzle, Projection pursuit regression, J. Amer. Statist. Assoc. 76 (1981) 817–823.
R. Gribonval, Approximations non-linéaires pour l'analyse de signaux sonores, Ph.D. thesis, Université Paris IX Dauphine (September 1999).
R. Gribonval, Fast matching pursuit with a multiscale dictionary of Gaussian chirps, to appear in IEEE Trans. Signal Process. (May 2001).
R. Gribonval, Ph. Depalle, X. Rodet, E. Bacry and S. Mallat, Sound signals decomposition using a high resolution matching pursuit, in: Proc. of Internat. Computer Music Conf. (ICMC'96), August 1996, pp. 293–296.
E. Hernández and G. Weiss, A First Course on Wavelets (CRC Press, Boca Raton, FL, 1996).
N. Hess-Nielsen and M.V. Wickerhauser, Wavelets and time-frequency analysis, Proc. IEEE 84(4) (1996) 523–540.
P.J. Huber, Projection pursuit, Ann. Statist. 13(2) (1985) 435–475.
S. Jaggi, W.C. Carl, S.Mallat and A.S.Willsky, High resolution pursuit for feature extraction, J. Appl. Comput. Harmonic Anal. 5(4) (1998) 428–449.
L.K. Jones, On a conjecture of Huber concerning the convergence of PP-regression, Ann. Statist. 15 (1987) 880–882.
E.D. Livschitz and V.N. Temlyakov, On convergence of weak greedy algorithms, Technical Report 0013, Department of Mathematics, University of South Carolina, Columbia, SC (2000); http:// www.math.sc.edu/~imip/00papers/0013.ps.
S. Mann and S. Haykin, The chirplet transform: Physical considerations, IEEE Trans. Signal Process. 43(11) (1995) 2745–2761.
S. Mallat and Z. Zhang, Matching pursuit with time-frequency dictionaries, IEEE Trans. Signal Process. 41(12) (1993) 3397–3415.
M.R. McClure and L. Carin, Matching pursuits with a wave-based dictionary, IEEE Trans. Signal Process. 45(12) (1997) 2912–2927.
S. Qian and D. Chen, Signal representation using adaptive normalized Gaussian functions, IEEE Trans. Signal Process. 36(1) (1994) 1–11.
V.N. Temlyakov, Weak greedy algorithms, Adv. Comput. Math. 12(2,3) (2000) 213–227.
V.N. Temlyakov, A criterion for convergence of Weak Greedy Algorithms, Technical Report 0021, Department of Mathematics, University of South Carolina, Columbia, SC (2000); http://www. math.sc.edu/~imip/00papers/0021.ps.
B. Torrésani, Wavelets associated with representations of the affine Weyl-Heisenberg group, J. Math. Phys. 32 (May 1991) 1273–1279.
M.V. Wickerhauser, Adapted Wavelet Analysis from Theory to Software (A.K. Peters, 1994).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Gribonval, R., Nielsen, M. Approximate Weak Greedy Algorithms. Advances in Computational Mathematics 14, 361–378 (2001). https://doi.org/10.1023/A:1012255021470
Issue Date:
DOI: https://doi.org/10.1023/A:1012255021470