Description: 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.
Price: 101 GBP
Location: Gloucester
End Time: 2025-01-18T16:45:08.000Z
Shipping Cost: 38.07 GBP
Product Images
Item Specifics
Return postage will be paid by: Buyer
Returns Accepted: Returns Accepted
After receiving the item, your buyer should cancel the purchase within: 60 days
Return policy details:
EAN: 9783030243616
UPC: 9783030243616
ISBN: 9783030243616
MPN: N/A
Book Title: Model Selection and Error Estimation in a Nutshell
Item Length: 23.4 cm
Number of Pages: 132 Pages
Publication Name: Model Selection and Error Estimation in a Nutshell
Language: English
Publisher: Springer Nature Switzerland A&G
Item Height: 235 mm
Subject: Computer Science, Mathematics
Publication Year: 2020
Type: Textbook
Item Weight: 238 g
Author: Luca Oneto
Item Width: 155 mm
Series: Modeling and Optimization in Science and Technologies
Format: Paperback
