Variational Bayesian learning theory / Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama.

Nakajima, Shin'ichi
Call Number
519.2/33
Author
Nakajima, Shin'ichi, author.
Title
Variational Bayesian learning theory / Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama.
Physical Description
1 online resource (xv, 543 pages) : digital, PDF file(s).
Notes
Title from publisher's bibliographic system (viewed on 28 Jun 2019).
Summary
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.
Added Author
Watanabe, Kazuho, author.
Sugiyama, Masashi, 1974- author.
Subject
Bayesian field theory.
PROBABILITIES.
Multimedia
Total Ratings: 0
No records found to display.
 
 
 
02357nam a22003858i 4500
001
 
 
vtls001584335
003
 
 
VRT
005
 
 
20200921121800.0
006
 
 
m|||||o||d||||||||
007
 
 
cr||||||||||||
008
 
 
200921s2019||||enk     o     ||1 0|eng|d
020
$a 9781139879354 (ebook)
020
$z 9781107076150 (hardback)
020
$z 9781107430761 (paperback)
035
$a (UkCbUP)CR9781139879354
039
9
$y 202009211218 $z santha
040
$a UkCbUP $b eng $e rda $c UkCbUP
050
0
0
$a QC174.85.B38 $b N35 2019
082
0
0
$a 519.2/33 $2 23
100
1
$a Nakajima, Shin'ichi, $e author.
245
1
0
$a Variational Bayesian learning theory / $c Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama.
264
1
$a Cambridge : $b Cambridge University Press, $c 2019.
300
$a 1 online resource (xv, 543 pages) : $b digital, PDF file(s).
336
$a text $b txt $2 rdacontent
337
$a computer $b c $2 rdamedia
338
$a online resource $b cr $2 rdacarrier
500
$a Title from publisher's bibliographic system (viewed on 28 Jun 2019).
520
$a 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.
650
0
$a Bayesian field theory.
650
0
$a PROBABILITIES.
700
1
$a Watanabe, Kazuho, $e author.
700
1
$a Sugiyama, Masashi, $d 1974- $e author.
776
0
8
$i Print version: $z 9781107076150
856
4
0
$u https://doi.org/10.1017/9781139879354
999
$a VIRTUA               
No Reviews to Display
Summary
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.
Notes
Title from publisher's bibliographic system (viewed on 28 Jun 2019).
Subject
Bayesian field theory.
PROBABILITIES.
Multimedia