Separability of reproducing kernel spaces

Owhadi, Houman; Scovel, Clint

doi:10.1090/proc/13354

Separability of reproducing kernel spaces
HTML articles powered by AMS MathViewer

by Houman Owhadi and Clint Scovel PDF

Proc. Amer. Math. Soc. 145 (2017), 2131-2138 Request permission

Abstract:

We demonstrate that a reproducing kernel Hilbert or Banach space of functions on a separable absolute Borel space or an analytic subset of a Polish space is separable if it possesses a Borel measurable feature map.

References

Charalambos D. Aliprantis and Kim C. Border, Infinite dimensional analysis, 3rd ed., Springer, Berlin, 2006. A hitchhiker’s guide. MR 2378491
Alain Berlinet and Christine Thomas-Agnan, Reproducing kernel Hilbert spaces in probability and statistics, Kluwer Academic Publishers, Boston, MA, 2004. With a preface by Persi Diaconis. MR 2239907, DOI 10.1007/978-1-4419-9096-9
Stamatis Cambanis, The measurability of a stochastic process of second order and its linear space, Proc. Amer. Math. Soc. 47 (1975), 467–475. MR 356206, DOI 10.1090/S0002-9939-1975-0356206-9
S. Canu, X. Mary, and A. Rakotomamonjy, Functional learning through kernels, Advances in Learning Theory: Methods, Models and Applications, NATO Science Series, vol. 190, IOS Press, 2003, pp. 89–110.
Jens Gerlach Christensen, Sampling in reproducing kernel Banach spaces on Lie groups, J. Approx. Theory 164 (2012), no. 1, 179–203. MR 2855776, DOI 10.1016/j.jat.2011.10.002
Andreas Christmann and Ingo Steinwart, Consistency of kernel-based quantile regression, Appl. Stoch. Models Bus. Ind. 24 (2008), no. 2, 171–183. MR 2406112, DOI 10.1002/asmb.700
Andreas Christmann and Ingo Steinwart, Universal kernels on non-standard input spaces, Advances in Neural Information Processing Systems 23, NIPS 2010, pp. 406–414.
Andreas Christmann, Arnout Van Messem, and Ingo Steinwart, On consistency and robustness properties of support vector machines for heavy-tailed distributions, Stat. Interface 2 (2009), no. 3, 311–327. MR 2540089, DOI 10.4310/SII.2009.v2.n3.a5
Ernesto De Vito, Lorenzo Rosasco, and Alessandro Toigo, Learning sets with separating kernels, Appl. Comput. Harmon. Anal. 37 (2014), no. 2, 185–217. MR 3223462, DOI 10.1016/j.acha.2013.11.003
Ernesto De Vito, Veronica Umanità, and Silvia Villa, An extension of Mercer theorem to matrix-valued measurable kernels, Appl. Comput. Harmon. Anal. 34 (2013), no. 3, 339–351. MR 3027907, DOI 10.1016/j.acha.2012.06.001
Claude Dellacherie and Paul-André Meyer, Probabilités et potentiel, Publications de l’Institut de Mathématique de l’Université de Strasbourg, No. XV, Hermann, Paris, 1975 (French). Chapitres I à IV; Édition entièrement refondue. MR 0488194
R. M. Dudley, Real analysis and probability, Cambridge Studies in Advanced Mathematics, vol. 74, Cambridge University Press, Cambridge, 2002. Revised reprint of the 1989 original. MR 1932358, DOI 10.1017/CBO9780511755347
Gregory E. Fasshauer, Fred J. Hickernell, and Qi Ye, Solving support vector machines in reproducing kernel Banach spaces with positive definite functions, Appl. Comput. Harmon. Anal. 38 (2015), no. 1, 115–139. MR 3273290, DOI 10.1016/j.acha.2014.03.007
R. Fortet, Espaces à noyau reproduisant et lois de probabilités des fonctions aléatoires, Ann. Inst. H. Poincaré Sect. B (N.S.) 9 (1973), 41–58 (French). MR 0345193
Zdeněk Frolík, On bianalytic spaces, Czechoslovak Math. J. 13(88) (1963), 561–573 (English, with Russian summary). MR 162216
Zdeněk Frolík, Absolute Borel and Souslin sets, Pacific J. Math. 32 (1970), 663–683. MR 265171
K. Fukumizu, G. R. Lanckriet, and B. K. Sriperumbudur, Learning in Hilbert vs. Banach spaces: A measure embedding viewpoint, Advances in Neural Information Processing Systems 24, NIPS 2011, pp. 1773–1781.
R. Hable and A. Christmann, Estimation of scale functions to model heteroscedasticity by regularised kernel-based quantile methods, J. Nonparametr. Stat. 26 (2014), no. 2, 219–239. MR 3195981, DOI 10.1080/10485252.2013.875547
Paul Richard Halmos, A Hilbert space problem book, 2nd ed., Encyclopedia of Mathematics and its Applications, vol. 17, Springer-Verlag, New York-Berlin, 1982. MR 675952
Deguang Han, M. Zuhair Nashed, and Qiyu Sun, Sampling expansions in reproducing kernel Hilbert and Banach spaces, Numer. Funct. Anal. Optim. 30 (2009), no. 9-10, 971–987. MR 2589760, DOI 10.1080/01630560903408606
R. W. Hansell, Sums, products and continuity of Borel maps in nonseparable metric spaces, Proc. Amer. Math. Soc. 104 (1988), no. 2, 465–471. MR 962814, DOI 10.1090/S0002-9939-1988-0962814-3
M. Hein and O. Bousquet, Kernels, associated structures and generalizations, Max-Planck-Institut fuer biologische Kybernetik, Technical Report (2004).
Alexander S. Kechris, Classical descriptive set theory, Graduate Texts in Mathematics, vol. 156, Springer-Verlag, New York, 1995. MR 1321597, DOI 10.1007/978-1-4612-4190-4
K. Kuratowski, Topology. Vol. I, Academic Press, New York-London; Państwowe Wydawnictwo Naukowe [Polish Scientific Publishers], Warsaw, 1966. New edition, revised and augmented; Translated from the French by J. Jaworowski. MR 0217751
Milan N. Lukić and Jay H. Beder, Stochastic processes with sample paths in reproducing kernel Hilbert spaces, Trans. Amer. Math. Soc. 353 (2001), no. 10, 3945–3969. MR 1837215, DOI 10.1090/S0002-9947-01-02852-5
Robert E. Megginson, An introduction to Banach space theory, Graduate Texts in Mathematics, vol. 183, Springer-Verlag, New York, 1998. MR 1650235, DOI 10.1007/978-1-4612-0603-3
D. Montgomery, Non-separable metric spaces, Fundamenta Mathematicae 1 (1935), no. 25, 527–533.
M. Zuhair Nashed and Gilbert G. Walter, General sampling theorems for functions in reproducing kernel Hilbert spaces, Math. Control Signals Systems 4 (1991), no. 4, 363–390. MR 1128261, DOI 10.1007/BF02570568
Richard Mansfield and Galen Weitkamp, Recursive aspects of descriptive set theory, Oxford Logic Guides, vol. 11, The Clarendon Press, Oxford University Press, New York, 1985. With a chapter by Stephen Simpson. MR 786122
Guohui Song, Haizhang Zhang, and Fred J. Hickernell, Reproducing kernel Banach spaces with the $\ell ^1$ norm, Appl. Comput. Harmon. Anal. 34 (2013), no. 1, 96–116. MR 2981335, DOI 10.1016/j.acha.2012.03.009
S. M. Srivastava, A course on Borel sets, Graduate Texts in Mathematics, vol. 180, Springer-Verlag, New York, 1998. MR 1619545, DOI 10.1007/978-3-642-85473-6
I. Steinwart, Convergence types and rates in generic Karhunen-Loève expansions with applications to sample path properties, arXiv:1403.1040 (2014).
Ingo Steinwart and Andreas Christmann, Support vector machines, Information Science and Statistics, Springer, New York, 2008. MR 2450103
Ingo Steinwart and Andreas Christmann, Sparsity of SVMs that use the $\epsilon$-insensitive loss, Advances in Neural Information Processing Systems 22, NIPS 2009, pp. 1569–1576.
Ingo Steinwart and Andreas Christmann, Estimating conditional quantiles with the help of the pinball loss, Bernoulli 17 (2011), no. 1, 211–225. MR 2797989, DOI 10.3150/10-BEJ267
Ingo Steinwart and Clint Scovel, Mercer’s theorem on general domains: on the interaction between measures, kernels, and RKHSs, Constr. Approx. 35 (2012), no. 3, 363–417. MR 2914365, DOI 10.1007/s00365-012-9153-3
A. H. Stone, Non-separable Borel sets, Rozprawy Mat. 28 (1962), 41. MR 152457
Vladimir Vovk, On-line regression competitive with reproducing kernel Hilbert spaces (extended abstract), Theory and applications of models of computation, Lecture Notes in Comput. Sci., vol. 3959, Springer, Berlin, 2006, pp. 452–463. MR 2277266, DOI 10.1007/11750321_{4}3
Stephen Willard, General topology, Addison-Wesley Publishing Co., Reading, Mass.-London-Don Mills, Ont., 1970. MR 0264581
Haizhang Zhang, Yuesheng Xu, and Jun Zhang, Reproducing kernel Banach spaces for machine learning, J. Mach. Learn. Res. 10 (2009), 2741–2775. MR 2579912, DOI 10.1109/IJCNN.2009.5179093
Haizhang Zhang and Jun Zhang, Frames, Riesz bases, and sampling expansions in Banach spaces via semi-inner products, Appl. Comput. Harmon. Anal. 31 (2011), no. 1, 1–25. MR 2795872, DOI 10.1016/j.acha.2010.09.007
Haizhang Zhang and Jun Zhang, Regularized learning in Banach spaces as an optimization problem: representer theorems, J. Global Optim. 54 (2012), no. 2, 235–250. MR 2979626, DOI 10.1007/s10898-010-9575-z