LEADER 03351nam  22005415  450 
001 9910483031303321
005 20200706201743.0
010   $a3-030-24359-1
024 7 $a10.1007/978-3-030-24359-3
035   $a(CKB)4100000008736989
035   $a(MiAaPQ)EBC5831111
035   $a(DE-He213)978-3-030-24359-3
035   $a(PPN)243770685
035   $a(EXLCZ)994100000008736989
100   $a20190717d2020      u|         0
101 0 $aeng
135   $aurcnu||||||||
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 10$aModel Selection and Error Estimation in a Nutshell /$fby Luca Oneto
205   $a1st ed. 2020.
210  1$aCham :$cSpringer International Publishing :$cImprint: Springer,$d2020.
215   $a1 online resource (135 pages)
225 1 $aModeling and Optimization in Science and Technologies,$x2196-7326 ;$v15
311   $a3-030-24358-3 
327   $aIntroduction -- The ?Five W? of MS & EE -- Preliminaries -- Resampling Methods -- Complexity-Based Methods -- Compression Bound -- Algorithmic Stability Theory -- PAC-Bayes Theory -- Di?erential Privacy Theory -- Conclusions & Further Readings.
330   $aHow can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80?s and includes the most recent results. It discusses open problems and outlines future directions for research.
410  0$aModeling and Optimization in Science and Technologies,$x2196-7326 ;$v15
606   $aComputational intelligence
606   $aStatistics 
606   $aData mining
606   $aComputational Intelligence$3https://scigraph.springernature.com/ontologies/product-market-codes/T11014
606   $aStatistical Theory and Methods$3https://scigraph.springernature.com/ontologies/product-market-codes/S11001
606   $aData Mining and Knowledge Discovery$3https://scigraph.springernature.com/ontologies/product-market-codes/I18030
615  0$aComputational intelligence.
615  0$aStatistics .
615  0$aData mining.
615 14$aComputational Intelligence.
615 24$aStatistical Theory and Methods.
615 24$aData Mining and Knowledge Discovery.
676   $a006.31
676   $a006.31
700   $aOneto$b Luca$4aut$4http://id.loc.gov/vocabulary/relators/aut$01080855
906   $aBOOK
912   $a9910483031303321
996   $aModel Selection and Error Estimation in a Nutshell$92854965
997   $aUNINA