東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Improved classification rates for lo...

Blaschzyk, Ingrid Karin.

Linked to FindBook

Google Book

Amazon

博客來

Improved classification rates for localized algorithms under margin conditions

Record Type:	Electronic resources : Monograph/item
Title/Author:	Improved classification rates for localized algorithms under margin conditions/ by Ingrid Karin Blaschzyk.
Author:	Blaschzyk, Ingrid Karin.
Published:	Wiesbaden :Springer Fachmedien Wiesbaden : : 2020.,
Description:	xv, 126 p. :ill., digital ;24 cm.
[NT 15003449]:	Introduction to Statistical Learning Theory -- Histogram Rule: Oracle Inequality and Learning Rates -- Localized SVMs: Oracle Inequalities and Learning Rates.
Contained By:	Springer eBooks
Subject:	Discriminant analysis. -
Online resource:	https://doi.org/10.1007/978-3-658-29591-2
ISBN:	9783658295912

Improved classification rates for localized algorithms under margin conditions
Blaschzyk, Ingrid Karin.

Improved classification rates for localized algorithms under margin conditions[electronic resource] /by Ingrid Karin Blaschzyk. - Wiesbaden :Springer Fachmedien Wiesbaden :2020. - xv, 126 p. :ill., digital ;24 cm.

Introduction to Statistical Learning Theory -- Histogram Rule: Oracle Inequality and Learning Rates -- Localized SVMs: Oracle Inequalities and Learning Rates.

Support vector machines (SVMs) are one of the most successful algorithms on small and medium-sized data sets, but on large-scale data sets their training and predictions become computationally infeasible. The author considers a spatially defined data chunking method for large-scale learning problems, leading to so-called localized SVMs, and implements an in-depth mathematical analysis with theoretical guarantees, which in particular include classification rates. The statistical analysis relies on a new and simple partitioning based technique and takes well-known margin conditions into account that describe the behavior of the data-generating distribution. It turns out that the rates outperform known rates of several other learning algorithms under suitable sets of assumptions. From a practical point of view, the author shows that a common training and validation procedure achieves the theoretical rates adaptively, that is, without knowing the margin parameters in advance. Contents Introduction to Statistical Learning Theory Histogram Rule: Oracle Inequality and Learning Rates Localized SVMs: Oracle Inequalities and Learning Rates Target Groups Researchers, students, and practitioners in the fields of mathematics and computer sciences who focus on machine learning or statistical learning theory The Author Ingrid Karin Blaschzyk is a postdoctoral researcher in the Department of Mathematics at the University of Stuttgart, Germany.

ISBN: 9783658295912

Standard No.: 10.1007/978-3-658-29591-2doiSubjects--Topical Terms:

560438
Discriminant analysis.

LC Class. No.: QA278.65 / .B537 2020

Dewey Class. No.: 519.535

Improved classification rates for localized algorithms under margin conditions
LDR:02620nmm a2200325 a 4500 001 2217225
003 DE-He213
005 20200806112040.0
006 m d
007 cr nn 008maaau
008 201120s2020 gw s 0 eng d
020 $a 9783658295912 $q (electronic bk.)
020 $a 9783658295905 $q (paper)
024 7 $a 10.1007/978-3-658-29591-2 $2 doi
035 $a 978-3-658-29591-2
040 $a GP $c GP
041 0 $a eng
050 4 $a QA278.65 $b .B537 2020
072 7 $a PBW $2 bicssc
072 7 $a MAT003000 $2 bisacsh
072 7 $a PBW $2 thema
082 0 4 $a 519.535 $2 23
090 $a QA278.65 $b .B644 2020
100 1 $a Blaschzyk, Ingrid Karin. $3 3450300
245 1 0 $a Improved classification rates for localized algorithms under margin conditions $h [electronic resource] / $c by Ingrid Karin Blaschzyk.
260 $a Wiesbaden : $b Springer Fachmedien Wiesbaden : $b Imprint: Springer Spektrum, $c 2020.
300 $a xv, 126 p. : $b ill., digital ; $c 24 cm.
505 0 $a Introduction to Statistical Learning Theory -- Histogram Rule: Oracle Inequality and Learning Rates -- Localized SVMs: Oracle Inequalities and Learning Rates.
520 $a Support vector machines (SVMs) are one of the most successful algorithms on small and medium-sized data sets, but on large-scale data sets their training and predictions become computationally infeasible. The author considers a spatially defined data chunking method for large-scale learning problems, leading to so-called localized SVMs, and implements an in-depth mathematical analysis with theoretical guarantees, which in particular include classification rates. The statistical analysis relies on a new and simple partitioning based technique and takes well-known margin conditions into account that describe the behavior of the data-generating distribution. It turns out that the rates outperform known rates of several other learning algorithms under suitable sets of assumptions. From a practical point of view, the author shows that a common training and validation procedure achieves the theoretical rates adaptively, that is, without knowing the margin parameters in advance. Contents Introduction to Statistical Learning Theory Histogram Rule: Oracle Inequality and Learning Rates Localized SVMs: Oracle Inequalities and Learning Rates Target Groups Researchers, students, and practitioners in the fields of mathematics and computer sciences who focus on machine learning or statistical learning theory The Author Ingrid Karin Blaschzyk is a postdoctoral researcher in the Department of Mathematics at the University of Stuttgart, Germany.
650 0 $a Discriminant analysis. $3 560438
650 0 $a Support vector machines. $3 2058743
650 1 4 $a Applications of Mathematics. $3 890893
650 2 4 $a Probability Theory and Stochastic Processes. $3 891080
650 2 4 $a Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences. $3 1005896
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer eBooks
856 4 0 $u https://doi.org/10.1007/978-3-658-29591-2
950 $a Mathematics and Statistics (Springer-11649)