Competing with wild prediction rules

Machine Learning

Volumn 69, Issue 2-3, 2007, Pages 193-212

  Vovk, Vladimir ^a  

^a UNIVERSITY OF LONDON   (United Kingdom)

Author keywords

Banach function space; Competitive on line prediction; Square loss regression

Indexed keywords

BANACH SPACES; BENCHMARKING; HILBERT SPACES; LEARNING ALGORITHMS; ONLINE SYSTEMS;

BANACH FUNCTION SPACE; COMPETITIVE ON-LINE PREDICTION; SQUARE LOSS REGRESSION; WILD PREDICTION RULES;

LOGIC PROGRAMMING;

EID: 35348927491     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1007/s10994-007-5021-y     Document Type: Conference Paper

References (33)

1. Adams, R. A., & Fournier, J. J. F. (2003). Pure and applied mathematics: Vol. 140. Sobolev spaces (2nd ed.). Amsterdam: Academic Press.
2. Aronszajn, N. (1950). Theory of reproducing kernels. Transactions of the American Mathematical Society, 68, 337-404.
3. Auer, P., Cesa-Bianchi, N., & Gentile, C. (2002). Adaptive and self-confident on-line learning algorithms. Journal of Computer and System Sciences, 64, 48-75.
4. Banaś, J. (1986). On moduli of smoothness of Banach spaces. Bulletin of the Polish Academy of Sciences. Mathematics, 34, 287-293.
5. Banaś, J., & Fra̧czek, K. (1993). Deformation of Banach spaces. Commentationes Mathematicae Universitatis Carolinae, 34, 47-53.
6. Bárcenas, D., Gurary, V. I., Sánchez, L., & Ullán, A. (2004). On moduli of convexity in Banach spaces. Quaestiones Mathematicae, 27, 137-145.
7. Cesa-Bianchi, N., Long, P. M., & Warmuth, M. K. (1996). Worst-case quadratic loss bounds for on-line prediction of linear functions by gradient descent. IEEE Transactions on Neural Networks, 7, 604-619.
8. Clarkson, J. A. (1936). Uniformly convex spaces. Transactions of the American Mathematical Society, 40, 396-414.
9. Cobos, F., & Edmunds, D. E. (1988). Clarkson's inequalities, Besov spaces and Triebel-Sobolev spaces. Zeitschrift für Analysis und ihre Anwendungen, 7, 229-232.
10. Edmunds, D. E., & Triebel, H. (1996). Cambridge tracts in mathematics: Vol. 120. Function spaces, entropy numbers, differential operators. Cambridge: Cambridge University Press.
11. Figiel, T. (1976). On the moduli of convexity and smoothness. Studia Mathematica, 56, 121-155.
12. Fuster, E. L. (2006). Moduli and constants:... what a show! Available on the Internet (accessed in July 2007).
13. Gurary, V. I. (1967). On differential properties of the convexity moduli of Banach spaces. Matematicheskie Issledovaniya, 2(1), 141-148 (in Russian).
14. p. Arkiv för Matematik, 3, 239-244.
15. Kivinen, J., & Warmuth, M. K. (1997). Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132, 1-63.
16. Kolmogorov, A. N. (1933). Grundbegriffe der Wahrscheinlichkeitsrechnung. Berlin: Springer. English translation: Foundations of the Theory of Probability. Chelsea, New York (1950).
17. Lindenstrauss, J. (1963). On the modulus of smoothness and divergent series in Banach spaces. Michigan Mathematical Journal, 10, 241-252.
18. Lindenstrauss, J., & Tzafriri, L. (1979). Ergebnisse der Mathematik und ihrer Grenzgebiete: Vol. 97. Classical Banach spaces II: function spaces. Berlin: Springer.
19. Liokumovich, V. I. (1973). The existence of B-spaces with non-convex modulus of convexity. Izvestiya Vysshikh Uchebnykh Zavedenii. Matematika, 12, 43-50 (in Russian).
20. Nikolsky, S. M. (1961). On embedding, continuation and approximation theorems for differentiable functions of several variables. Russian Mathematical Surveys, 16(5), 55-104.
21. Nördlander, G. (1960). The modulus of convexity in normed linear spaces. Arkiv för Matematik, 4, 15-17.
22. Press, W. H., Flannery, B. P., Teukolsky, S. A., & Vetterling, W. T. (1992). Numerical recipes in C (2nd ed.). Cambridge: Cambridge University Press.
23. Rockafellar, R. T. (1970). Convex analysis. Princeton: Princeton University Press.
24. Rudin, W. (1991). Functional analysis. International series in pure and applied mathematics (2nd ed.). Boston: McGraw-Hill.
25. Steinwart, I. (2001). On the influence of the kernel on the consistency of support vector machines. Journal of Machine Learning Research, 2, 67-93.
26. r (X). Mathematische Nachrichten, 188, 341-348.
27. Triebel, H. (1983). Monographs in mathematics: Vol. 78. Theory of function spaces. Basel: Birkhäuser.
28. Triebel, H. (1992). Monographs in mathematics: Vol. 84. Theory of function spaces II. Basel: Birkhäuser.
29. Triebel, H. (2005). Sampling numbers and embedding constants. Proceedings of the Steklov Institute of Mathematics, 248, 268-277.
30. Vovk, V. (2005). Defensive prediction with expert advice. In S. Jain, H. U. Simon & E. Tomita (Eds.), Lecture notes in artificial intelligence : Vol. 3734. Proceedings of the sixteenth international conference on algorithmic learning theory (pp. 444-458). Berlin: Springer. Full version: Technical report. arXiv:cs.LG/0506041 "Competitive on-line learning with a convex loss function" (version 3), arXiv.org e-Print archive, September 2005.
31. Vovk, V. (2006a). On-line regression competitive with reproducing kernel Hilbert spaces. In J.-Y. Cai, S. B. Cooper & A. Li (Eds.), Lecture notes in computer science : Vol. 3959. Theory and applications of models of computation. Proceedings of the third annual conference on computation and logic (pp. 452-463). Berlin: Springer. Full version: Technical report. arXiv:cs.LG/0511058, arXiv.org e-Print archive, January 2006.
32. Vovk, V. (2006b). Competing with wild prediction rules. In G. Lugosi & H. U. Simon (Eds.), Lecture notes in artificial intelligence : Vol. 4005. Proceedings of the nineteenth annual conference on learning theory (pp. 559-573). Berlin: Springer. This is the conference version of this paper.
33. Vovk, V. (2006c). Metric entropy in competitive on-line prediction. Technical report. arXiv:cs.LG/0609045, arXiv.org e-Print archive.