en-de
en-es
en-fr
en-pt
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Online Variational Inference for the Hierarchical Dirichlet Process
Published on May 06, 20115974 Views
The hierarchical Dirichlet process (HDP) is a Bayesian nonparametric model that can be used to model mixed-membership data with a potentially infinite number of components. It has been applied wid
Related categories
Chapter list
Online Variational Inference for the Hierarchical Dirichlet Process00:00
Why Online Variational Inference for the HDP00:06
Outline01:02
Why a new batch variational inference algorithm?01:28
The HDP topic model02:04
Sethuraman's stick breaking for the DP03:08
Sethuraman's stick breaking for the HDP04:39
A new batch variational inference algorithm05:49
A new batch variational inference algorithm - cont'06:59
The batch variational inference algorithm flow08:11
The batch variational inference algorithm flow09:06
Stochastic gradient10:00
Stochastic gradient - cont'10:38
The online variational inference with natural gradient12:07
The nal online variational inference algorithm13:40
Data, Metric and Comparisons14:55
Results on Nature15:56
Results on PNAS17:25
Results on PNAS - cont'18:12
Results on streaming data - simulated on Nature18:36
Summary19:36
References20:13