Trudy Matematicheskogo Instituta imeni V.A. Steklova
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Forthcoming papers
Archive
Impact factor
Guidelines for authors
License agreement

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Trudy Mat. Inst. Steklova:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Trudy Matematicheskogo Instituta imeni V.A. Steklova, 2006, Volume 255, Pages 256–272 (Mi tm268)  

This article is cited in 4 scientific papers (total in 4 papers)

On Universal Estimators in Learning Theory

V. N. Temlyakov

University of South Carolina
Full-text PDF (262 kB) Citations (4)
References:
Abstract: This paper addresses the problem of constructing and analyzing estimators for the regression problem in supervised learning. Recently, there has been great interest in studying universal estimators. The term “universal” means that, on the one hand, the estimator does not depend on the a priori assumption that the regression function fρfρ belongs to some class FF from a collection of classes FF and, on the other hand, the estimation error for fρfρ is close to the optimal error for the class FF. This paper is an illustration of how the general technique of constructing universal estimators, developed in the author's previous paper, can be applied in concrete situations. The setting of the problem studied in the paper has been motivated by a recent paper by Smale and Zhou. The starting point for us is a kernel K(x,u)K(x,u) defined on X×ΩX×Ω. On the base of this kernel, we build an estimator that is universal for classes defined in terms of nonlinear approximations with regard to the system {K(,u)}uΩ{K(,u)}uΩ. To construct an easily implementable estimator, we apply the relaxed greedy algorithm.
Received in January 2006
English version:
Proceedings of the Steklov Institute of Mathematics, 2006, Volume 255, Pages 244–259
DOI: https://doi.org/10.1134/S0081543806040201
Bibliographic databases:
UDC: 517.5
Language: Russian
Citation: V. N. Temlyakov, “On Universal Estimators in Learning Theory”, Function spaces, approximation theory, and nonlinear analysis, Collected papers, Trudy Mat. Inst. Steklova, 255, Nauka, MAIK «Nauka/Inteperiodika», M., 2006, 256–272; Proc. Steklov Inst. Math., 255 (2006), 244–259
Citation in format AMSBIB
\Bibitem{Tem06}
\by V.~N.~Temlyakov
\paper On Universal Estimators in Learning Theory
\inbook Function spaces, approximation theory, and nonlinear analysis
\bookinfo Collected papers
\serial Trudy Mat. Inst. Steklova
\yr 2006
\vol 255
\pages 256--272
\publ Nauka, MAIK «Nauka/Inteperiodika»
\publaddr M.
\mathnet{http://mi.mathnet.ru/tm268}
\mathscinet{http://mathscinet.ams.org/mathscinet-getitem?mr=2302836}
\transl
\jour Proc. Steklov Inst. Math.
\yr 2006
\vol 255
\pages 244--259
\crossref{https://doi.org/10.1134/S0081543806040201}
\scopus{https://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-33846857278}
Linking options:
  • https://www.mathnet.ru/eng/tm268
  • https://www.mathnet.ru/eng/tm/v255/p256
  • This publication is cited in the following 4 articles:
    1. V. N. Temlyakov, “On Universal Sampling Recovery in the Uniform Norm”, Proc. Steklov Inst. Math., 323 (2023), 206–216  mathnet  crossref  crossref  mathscinet
    2. Temlyakov V.N., “Smooth Fixed Volume Discrepancy, Dispersion, and Related Problems”, J. Approx. Theory, 237 (2019), 113–134  crossref  mathscinet  zmath  isi  scopus
    3. Vladimir Temlyakov, “Connections between numerical integration, discrepancy, dispersion, and universal discretization”, The SMAI journal of computational mathematics, S5 (2019), 185  crossref
    4. Temlyakov V.N., “Universal Discretization”, J. Complex., 47 (2018), 97–109  crossref  mathscinet  zmath  isi  scopus
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Труды Математического института имени В. А. Стеклова Proceedings of the Steklov Institute of Mathematics
    Statistics & downloads:
    Abstract page:392
    Full-text PDF :115
    References:56
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2025