zbMATH — the first resource for mathematics

Geometry Search for the term Geometry in any field. Queries are case-independent.
Funct* Wildcard queries are specified by * (e.g. functions, functorial, etc.). Otherwise the search is exact.
"Topological group" Phrases (multi-words) should be set in "straight quotation marks".
au: Bourbaki & ti: Algebra Search for author and title. The and-operator & is default and can be omitted.
Chebyshev | Tschebyscheff The or-operator | allows to search for Chebyshev or Tschebyscheff.
"Quasi* map*" py: 1989 The resulting documents have publication year 1989.
so: Eur* J* Mat* Soc* cc: 14 Search for publications in a particular source with a Mathematics Subject Classification code (cc) in 14.
"Partial diff* eq*" ! elliptic The not-operator ! eliminates all results containing the word elliptic.
dt: b & au: Hilbert The document type is set to books; alternatively: j for journal articles, a for book articles.
py: 2000-2015 cc: (94A | 11T) Number ranges are accepted. Terms can be grouped within (parentheses).
la: chinese Find documents in a given language. ISO 639-1 language codes can also be used.

a & b logic and
a | b logic or
!ab logic not
abc* right wildcard
"ab c" phrase
(ab c) parentheses
any anywhere an internal document identifier
au author, editor ai internal author identifier
ti title la language
so source ab review, abstract
py publication year rv reviewer
cc MSC code ut uncontrolled term
dt document type (j: journal article; b: book; a: book article)
Learning with varying insensitive loss. (English) Zbl 1228.62052
Summary: Support vector machines for regression are implemented based on regularization schemes in reproducing kernel Hilbert spaces associated with an ε-insensitive loss. The insensitive parameter ε>0 changes with the sample size and plays a crucial role in the learning algorithm. The purpose of this paper is to present a perturbation theorem to show how the medium function of the probability measure for regression (with ε=0) can be approximated by learning the minimizer of the generalization error with sufficiently small parameter ε>0. A concrete learning rate is provided under a regularity condition of the medium function and a noise condition of the probability measure.
62G08Nonparametric regression
46N30Applications of functional analysis in probability theory and statistics
68T05Learning and adaptive systems
[1]Vapnik, V.: Statistical learning theory, (1998) · Zbl 0935.62007
[2]Steinwart, I.; Christmann, A.: Support vector machines, (2008)
[3]Tong, H. Z.; Chen, D. R.; Peng, L. Z.: Analysis of support vector machines regression, Found. comput. Math. 9, 243-257 (2009) · Zbl 1185.68577 · doi:10.1007/s10208-008-9026-0
[4]Rieger, C.; Zwicknagl, B.: Deterministic error analysis of support vector regression and related regularized kernel methods, J. Mach learn. Res. 10, 2115-2132 (2009)
[5]Steinwart, I.; Christman, A.: Estimating conditional quantiles with the help of the pinball loss, Bernoulli 17, 211-225 (2011)
[6]Wu, Q.; Ying, Y.; Zhou, D. X.: Learning rates of least-square regularized regression, Found. comput. Math. 6, 171-192 (2006) · Zbl 1100.68100 · doi:10.1007/s10208-004-0155-9
[7]Smale, S.; Zhou, D. X.: Shannon sampling II. Connections to learning theory, Appl. comput. Harmon. anal. 19, 285-302 (2005) · Zbl 1107.94008 · doi:10.1016/j.acha.2005.03.001
[8]Smale, S.; Zhou, D. X.: Online learning with Markov sampling, Anal. appl. 7, 87-113 (2009) · Zbl 1170.68022 · doi:10.1142/S0219530509001293
[9]Yao, Y.: On complexity issue of online learning algorithms, IEEE trans. Inform. theory 56, 6470-6481 (2010)