View in EDS PDF Full Text

Variational Bayesian Learning Theory

Saved in:
Bibliographic Details
Title: Variational Bayesian Learning Theory
Description: Variational Bayesian learning is one of the most popular methods in machine learning. Designed for researchers and graduate students in machine learning, this book summarizes recent developments in the non-asymptotic and asymptotic theory of variational Bayesian learning and suggests how this theory can be applied in practice. The authors begin by developing a basic framework with a focus on conjugacy, which enables the reader to derive tractable algorithms. Next, it summarizes non-asymptotic theory, which, although limited in application to bilinear models, precisely describes the behavior of the variational Bayesian solution and reveals its sparsity inducing mechanism. Finally, the text summarizes asymptotic theory, which reveals phase transition phenomena depending on the prior setting, thus providing suggestions on how to set hyperparameters for particular purposes. Detailed derivations allow readers to follow along without prior knowledge of the mathematical techniques specific to Bayesian learning.
Authors: Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama
Resource Type: eBook.
Subjects: Bayesian field theory, Probabilities
Categories: COMPUTERS / Artificial Intelligence / Computer Vision & Pattern Recognition
Database: eBook Collection (EBSCOhost)
FullText Links:
  – Type: ebook-pdf
Text:
  Availability: 0
Header DbId: nlebk
DbLabel: eBook Collection (EBSCOhost)
An: 2172661
RelevancyScore: 1090
AccessLevel: 6
PubType: eBook
PubTypeId: ebook
PreciseRelevancyScore: 1090.09973144531
IllustrationInfo
ImageInfo – Size: thumb
  Target: https://rps2images.ebscohost.com/rpsweb/othumb?id=NL$2172661$PDF&s=r
– Size: medium
  Target: https://rps2images.ebscohost.com/rpsweb/othumb?id=NL$2172661$PDF&s=d
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Variational Bayesian Learning Theory
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Variational Bayesian learning is one of the most popular methods in machine learning. Designed for researchers and graduate students in machine learning, this book summarizes recent developments in the non-asymptotic and asymptotic theory of variational Bayesian learning and suggests how this theory can be applied in practice. The authors begin by developing a basic framework with a focus on conjugacy, which enables the reader to derive tractable algorithms. Next, it summarizes non-asymptotic theory, which, although limited in application to bilinear models, precisely describes the behavior of the variational Bayesian solution and reveals its sparsity inducing mechanism. Finally, the text summarizes asymptotic theory, which reveals phase transition phenomena depending on the prior setting, thus providing suggestions on how to set hyperparameters for particular purposes. Detailed derivations allow readers to follow along without prior knowledge of the mathematical techniques specific to Bayesian learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Shinichi+Nakajima%22">Shinichi Nakajima</searchLink><br /><searchLink fieldCode="AR" term="%22Kazuho+Watanabe%22">Kazuho Watanabe</searchLink><br /><searchLink fieldCode="AR" term="%22Masashi+Sugiyama%22">Masashi Sugiyama</searchLink>
– Name: TypePub
  Label: Resource Type
  Group: TypPub
  Data: eBook.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Bayesian+field+theory%22">Bayesian field theory</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilities%22">Probabilities</searchLink>
– Name: SubjectBISAC
  Label: Categories
  Group: Su
  Data: <searchLink fieldCode="ZK" term="%22COMPUTERS+%2F+Artificial+Intelligence+%2F+Computer+Vision+%26+Pattern+Recognition%22">COMPUTERS / Artificial Intelligence / Computer Vision & Pattern Recognition</searchLink>
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=nlebk&AN=2172661
RecordInfo BibRecord:
  BibEntity:
    Classifications:
      – Code: 519.233
        Scheme: ddc
        Type: prePub
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Bayesian field theory
        Type: general
      – SubjectFull: Probabilities
        Type: general
    Titles:
      – TitleFull: Variational Bayesian Learning Theory
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Shinichi Nakajima
      – PersonEntity:
          Name:
            NameFull: Kazuho Watanabe
      – PersonEntity:
          Name:
            NameFull: Masashi Sugiyama
      – PersonEntity:
          Name:
            NameFull: Shinichi Nakajima
      – PersonEntity:
          Name:
            NameFull: Kazuho Watanabe
      – PersonEntity:
          Name:
            NameFull: Masashi Sugiyama
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2019
            – D: 23
              M: 08
              Type: profile
              Y: 2019
          Identifiers:
            – Type: isbn-print
              Value: 9781107076150
            – Type: isbn-electronic
              Value: 9781316998311
          Titles:
            – TitleFull: Variational Bayesian Learning Theory
              Type: main
ResultId 1