國立虎尾科技大學 |

Model Selection and Error Estimation in a Nutshell

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Model Selection and Error Estimation in a Nutshell/ by Luca Oneto.
Author:	Oneto, Luca.
Description:	XIII, 132 p. 62 illus.online resource. :
Contained By:	Springer Nature eBook
Subject:	Computational intelligence. -
Online resource:	https://doi.org/10.1007/978-3-030-24359-3
ISBN:	9783030243593

Model Selection and Error Estimation in a Nutshell
Oneto, Luca.

Model Selection and Error Estimation in a Nutshell[electronic resource] /by Luca Oneto. - 1st ed. 2020. - XIII, 132 p. 62 illus.online resource. - Modeling and Optimization in Science and Technologies,152196-7326 ;. - Modeling and Optimization in Science and Technologies,4.

Introduction -- The “Five W” of MS & EE -- Preliminaries -- Resampling Methods -- Complexity-Based Methods -- Compression Bound -- Algorithmic Stability Theory -- PAC-Bayes Theory -- Diﬀerential Privacy Theory -- Conclusions & Further Readings.

How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80’s and includes the most recent results. It discusses open problems and outlines future directions for research.

ISBN: 9783030243593

Standard No.: 10.1007/978-3-030-24359-3doiSubjects--Topical Terms:

568984
Computational intelligence.

LC Class. No.: Q342

Dewey Class. No.: 006.3

Model Selection and Error Estimation in a Nutshell
LDR:02765nam a22004095i 4500 001 1026455
003 DE-He213
005 20200706201743.0
007 cr nn 008mamaa
008 210318s2020 gw | s |||| 0|eng d
020 $a 9783030243593 $9 978-3-030-24359-3
024 7 $a 10.1007/978-3-030-24359-3 $2 doi
035 $a 978-3-030-24359-3
050 4 $a Q342
072 7 $a UYQ $2 bicssc
072 7 $a TEC009000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.3 $2 23
100 1 $a Oneto, Luca. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1285106
245 1 0 $a Model Selection and Error Estimation in a Nutshell $h [electronic resource] / $c by Luca Oneto.
250 $a 1st ed. 2020.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a XIII, 132 p. 62 illus. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Modeling and Optimization in Science and Technologies, $x 2196-7326 ; $v 15
505 0 $a Introduction -- The “Five W” of MS & EE -- Preliminaries -- Resampling Methods -- Complexity-Based Methods -- Compression Bound -- Algorithmic Stability Theory -- PAC-Bayes Theory -- Diﬀerential Privacy Theory -- Conclusions & Further Readings.
520 $a How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80’s and includes the most recent results. It discusses open problems and outlines future directions for research.
650 0 $a Computational intelligence. $3 568984
650 0 $a Statistics . $3 1253516
650 0 $a Data mining. $3 528622
650 1 4 $a Computational Intelligence. $3 768837
650 2 4 $a Statistical Theory and Methods. $3 671396
650 2 4 $a Data Mining and Knowledge Discovery. $3 677765
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030243586
776 0 8 $i Printed edition: $z 9783030243609
776 0 8 $i Printed edition: $z 9783030243616
830 0 $a Modeling and Optimization in Science and Technologies, $x 2196-7326 ; $v 4 $3 1258709
856 4 0 $u https://doi.org/10.1007/978-3-030-24359-3
912 $a ZDB-2-INR
912 $a ZDB-2-SXIT
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)
950 $a Intelligent Technologies and Robotics (R0) (SpringerNature-43728)