عنوان

Model selection and error estimation in a nutshell /

(Number (ISBN

3030243591

(Number (ISBN

9783030243593

Erroneous ISBN

9783030243586

Title Proper

Model selection and error estimation in a nutshell /

General Material Designation

[Book]

First Statement of Responsibility

Luca Oneto.

Place of Publication, Distribution, etc.

Cham, Switzerland :

Name of Publisher, Distributor, etc.

Springer Nature,

Date of Publication, Distribution, etc.

[2020]

Date of Publication, Distribution, etc.

©2020

Specific Material Designation and Extent of Item

1 online resource.

Series Title

Modeling and optimization in science and technologies ;

Volume Designation

v. 15

Text of Note

Includes bibliographical references and index.

Text of Note

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.

0

Text of Note

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.

Source for Acquisition/Subscription Address

Springer Nature

Stock Number

com.springer.onix.9783030243593

Algorithms.

Computational learning theory.

Machine learning.

Algorithms.

Computational learning theory.

Machine learning.

Number

Edition

Class number

Oneto, Luca

Date of Transaction

20200823093154.0

Cataloguing Rules (Descriptive Conventions))

pn

Electronic name

[Book]

Y