Remote Access Proceedings of the American Mathematical Society
Green Open Access

Proceedings of the American Mathematical Society

ISSN 1088-6826(online) ISSN 0002-9939(print)

 
 

 

Separability of reproducing kernel spaces


Authors: Houman Owhadi and Clint Scovel
Journal: Proc. Amer. Math. Soc. 145 (2017), 2131-2138
MSC (2010): Primary 46E22
DOI: https://doi.org/10.1090/proc/13354
Published electronically: October 27, 2016
Full-text PDF

Abstract | References | Similar Articles | Additional Information

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 [Enhancements On Off] (What's this?)

  • [1] Charalambos D. Aliprantis and Kim C. Border, Infinite dimensional analysis: A hitchhiker's guide, 3rd ed., Springer, Berlin, 2006. MR 2378491
  • [2] Alain Berlinet and Christine Thomas-Agnan, Reproducing kernel Hilbert spaces in probability and statistics, with a preface by Persi Diaconis, Kluwer Academic Publishers, Boston, MA, 2004. With a preface by Persi Diaconis. MR 2239907
  • [3] Stamatis Cambanis, The measurability of a stochastic process of second order and its linear space, Proc. Amer. Math. Soc. 47 (1975), 467-475. MR 0356206
  • [4] 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.
  • [5] Jens Gerlach Christensen, Sampling in reproducing kernel Banach spaces on Lie groups, J. Approx. Theory 164 (2012), no. 1, 179-203. MR 2855776, https://doi.org/10.1016/j.jat.2011.10.002
  • [6] Andreas Christmann and Ingo Steinwart, Consistency of kernel-based quantile regression, Appl. Stoch. Models Bus. Ind. 24 (2008), no. 2, 171-183. MR 2406112, https://doi.org/10.1002/asmb.700
  • [7] Andreas Christmann and Ingo Steinwart, Universal kernels on non-standard input spaces, Advances in Neural Information Processing Systems 23, NIPS 2010, pp. 406-414.
  • [8] 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, https://doi.org/10.4310/SII.2009.v2.n3.a5
  • [9] 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, https://doi.org/10.1016/j.acha.2013.11.003
  • [10] 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, https://doi.org/10.1016/j.acha.2012.06.001
  • [11] Claude Dellacherie and Paul-André Meyer, Probabilités et potentiel (French). Chapitres I à IV; Édition entièrement refondue; Publications de l'Institut de Mathématique de l'Université de Strasbourg, No. XV; Actualités Scientifiques et Industrielles, No. 1372, Hermann, Paris, 1975. MR 0488194
  • [12] 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
  • [13] 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, https://doi.org/10.1016/j.acha.2014.03.007
  • [14] 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
  • [15] Zdeněk Frolík, On bianalytic spaces, Czechoslovak Math. J. 13 (88) (1963), 561-573 (English, with Russian summary). MR 0162216
  • [16] Zdeněk Frolík, Absolute Borel and Souslin sets, Pacific J. Math. 32 (1970), 663-683. MR 0265171
  • [17] 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.
  • [18] 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, https://doi.org/10.1080/10485252.2013.875547
  • [19] Paul Richard Halmos, A Hilbert space problem book, 2nd ed., Encyclopedia of Mathematics and its Applications, 17, Graduate Texts in Mathematics, vol. 19, Springer-Verlag, New York-Berlin, 1982. MR 675952
  • [20] 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, https://doi.org/10.1080/01630560903408606
  • [21] 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, https://doi.org/10.2307/2046996
  • [22] M. Hein and O. Bousquet, Kernels, associated structures and generalizations, Max-Planck-Institut fuer biologische Kybernetik, Technical Report (2004).
  • [23] Alexander S. Kechris, Classical descriptive set theory, Graduate Texts in Mathematics, vol. 156, Springer-Verlag, New York, 1995. MR 1321597
  • [24] K. Kuratowski, Topology. Vol. I, New edition, revised and augmented. Translated from the French by J. Jaworowski, Academic Press, New York-London; Państwowe Wydawnictwo Naukowe, Warsaw, 1966. MR 0217751
  • [25] 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, https://doi.org/10.1090/S0002-9947-01-02852-5
  • [26] Robert E. Megginson, An introduction to Banach space theory, Graduate Texts in Mathematics, vol. 183, Springer-Verlag, New York, 1998. MR 1650235
  • [27] D. Montgomery, Non-separable metric spaces, Fundamenta Mathematicae 1 (1935), no. 25, 527-533.
  • [28] 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, https://doi.org/10.1007/BF02570568
  • [29] S. Simpson, BQO theory and Fraïssé's conjecture, Recursive Aspects of Descriptive Set Theory, Oxford University Press, Oxford (1985). MR 786122
  • [30] 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, https://doi.org/10.1016/j.acha.2012.03.009
  • [31] S. M. Srivastava, A course on Borel sets, Graduate Texts in Mathematics, vol. 180, Springer-Verlag, New York, 1998. MR 1619545
  • [32] I. Steinwart, Convergence types and rates in generic Karhunen-Loève expansions with applications to sample path properties, arXiv:1403.1040 (2014).
  • [33] Ingo Steinwart and Andreas Christmann, Support vector machines, Information Science and Statistics, Springer, New York, 2008. MR 2450103
  • [34] 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.
  • [35] Ingo Steinwart and Andreas Christmann, Estimating conditional quantiles with the help of the pinball loss, Bernoulli 17 (2011), no. 1, 211-225. MR 2797989, https://doi.org/10.3150/10-BEJ267
  • [36] 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, https://doi.org/10.1007/s00365-012-9153-3
  • [37] A. H. Stone, Non-separable Borel sets, Rozprawy Mat. 28 (1962), 41 pp.. MR 0152457
  • [38] 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, https://doi.org/10.1007/11750321_43
  • [39] Stephen Willard, General topology, Addison-Wesley Publishing Co., Reading, Mass.-London-Don Mills, Ont., 1970. MR 0264581
  • [40] Haizhang Zhang, Yuesheng Xu, and Jun Zhang, Reproducing kernel Banach spaces for machine learning, J. Mach. Learn. Res. 10 (2009), 2741-2775. MR 2579912, https://doi.org/10.1109/IJCNN.2009.5179093
  • [41] 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, https://doi.org/10.1016/j.acha.2010.09.007
  • [42] 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, https://doi.org/10.1007/s10898-010-9575-z

Similar Articles

Retrieve articles in Proceedings of the American Mathematical Society with MSC (2010): 46E22

Retrieve articles in all journals with MSC (2010): 46E22


Additional Information

Houman Owhadi
Affiliation: Department of Computing and Mathematical Sciences, California Institute of Technology, MC 9-94, Pasadena, California 91125
Email: owhadi@caltech.edu

Clint Scovel
Affiliation: Department of Computing and Mathematical Sciences, California Institute of Technology, MC 9-94, Pasadena, California 91125
Email: clintscovel@gmail.com

DOI: https://doi.org/10.1090/proc/13354
Received by editor(s): July 13, 2015
Received by editor(s) in revised form: March 3, 2016, May 31, 2016, and July 5, 2016
Published electronically: October 27, 2016
Communicated by: Mark M. Meerschaert
Article copyright: © Copyright 2016 American Mathematical Society

American Mathematical Society