Improved minimax bounds on the test and training distortion of empirically designed vector quantizers

IEEE Transactions on Information Theory

Volumn 51, Issue 11, 2005, Pages 4022-4032

  Antos, András ^a  

^a INSTITUTE OF EXPERIMENTAL MEDICINE   (Hungary)

Author keywords

Clustering methods; Distortion; Empirical design; Lower bounds; Minimax control; Redundancy; Training; Vector quantization

Indexed keywords

OPTIMIZATION; PROBABILITY; REDUNDANCY; SIGNAL DISTORTION; THEOREM PROVING; VECTOR QUANTIZATION;

CLUSTERING METHODS; EMPIRICAL DESIGN; LOWER BOUNDS; MINIMAX CONTROL;

DATA COMPRESSION;

EID: 27744461035     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2005.856980     Document Type: Article

References (18)

1. D. Pollard, "Strong consistency of k-means clustering," Ann. Statist., vol. 9, no. 1, pp. 135-140, 1981.
2. D. Pollard, "Quantization and the method of k-means," IEEE Trans. Inf. Theory, vol. IT-28, no. 2, pp. 199-205, Mar. 1982. 16.
3. T. Linder, G. Lugosi, and K. Zeger, "Rates of convergence in the source coding theorem, in empirical quantizer design, and in universal lossy source coding," IEEE Trans. Inf. Theory, vol. 40, no. 6, pp. 1728-1740, Nov. 1994.
4. T. Linder, "On the training distortion of vector quantizers," IEEE Trans. Inf. Theory, vol. 46, no. 4, pp. 1617-1623, Jul. 2000.
5. T. Linder, "Learning-theoretic methods in vector quantization," in Principles of Nonparametric Learning, ser. CISM Courses and Lectures, L. Györfi, Ed. Wien, New York: Springer-Verlag, 2002, ch. 4, pp. 163-210.
6. T. Linder, G. Lugosi, and K. Zeger, "Empirical quantizer design in the presence of source noise or channel noise," IEEE Trans. Inf. Theory, vol. 43, no. 2, pp. 612-623, Mar. 1997.
7. N. Merhav and J. Ziv, "On the amount of side information required for lossy data compression," IEEE Trans. Inf. Theory, vol. 43, no. 4, pp. 1112-1121, Jul. 1997.
8. A. J. Zeevi, "On the performance of vector quantizers empirically designed from dependent sources," in Proc. Data Compression Conf. (DCC'98), J. Storer and M. Cohn, Eds. Los Alamitos, CA: IEEE Comp. Soc. Press, 1998, pp. 73-82.
9. P. C. Cosman, K. O. Perlmutter, S. M. Perlmutter, R. A. Olshen, and R. M. Gray, "Training sequence size and vector quantizer performance," in Proc. Asilomar Conf. Signals, Systems, and Computers, Pacific Grove, CA, Nov. 1991, pp. 434-438.
10. D. Cohn, E. Riskin, and R. Ladner, "Theory and practice of vector quantizers trained on small training sets," IEEE Trans. Patt. Anal. Mach. Intell., vol. 16, no. 1, pp. 5M5, Jan. 1994.
11. P. Bartlett, T. Linder, and G. Lugosi, "The minimax distortion redundancy in empirical quantizer design," IEEE Trans. Inf. Theory, vol. 44, no. 5, pp. 1802-1813, Sep. 1998.
12. A. Antos, L. Györfi, and A. György, "Individual convergence rates in empirical vector quantizer design," IEEE Trans. Inf. Theory, vol. 51, no. 11, pp. 4013-4022, Nov. 2005.
13. p (1/n)," in Proc. IEEE Int. Symp. Information Theory, Trondheim, Norway, Jun./Jul. 1994, p. 457.
14. D. Pollard, "A central limit theorem for k-means clustering," Ann. Probab., vol. 10, no. 4, pp. 919-926, 1982.
15. L. Devroye, L. Györfi, and G. Lugosi, A Probabilistic Theory of Pattern Recognition, ser. Applications of Mathematics, Stochastic Modeling and Applied Probability. New York: Springer-Verlag, 1996.
16. E. V. Slud, "Distribution inequalities for the binomial law," Ann. Probab., vol. 5, pp. 404-412, 1977.
17. A. N. Kolmogorov and V. M. Tikhomirov, "∈-entropy and ∈-capacity of sets in function spaces," Transl. Amer. Math. Soc., vol. 17, pp. 277-364, 1961.
18. 1 View. New York: Wiley, 1985.