en
0.25
0.5
0.75
1.25
1.5
1.75
2
Graphical Models via Generalized Linear Models
Published on Jan 16, 20135681 Views
Undirected graphical models, or Markov networks, such as Gaussian graphical models and Ising models enjoy popularity in a variety of applications. In many settings, however, data may not follow a Gaus
Related categories
Chapter list
Graphical Models via Generalized Linear Models00:00
Review: Undirected Graphical Models / Markov Random Fields (MRFs)00:15
Applications of MRFs - Discrete Data01:20
Applications of MRFs - Continuous Data01:52
Motivation of our work02:23
Univariate Distributions for Different Data Types (1)03:21
Univariate Distributions for Different Data Types (2)04:02
Univariate Distributions for Different Data Types (3)04:36
Review: Exponential Families04:44
Univariate Exponential Families → Graphical Models (1)05:06
Univariate Exponential Families → Graphical Models (2)05:47
Exponential Family Markov Random Fields (1)06:00
Exponential Family Markov Random Fields (2)06:54
Exponential Family Markov Random Fields (3)07:07
Exponential Family MRFs - Example: GLM Graphical Models (1)07:48
Exponential Family MRFs - Example: GLM Graphical Models (2)08:04
Exponential Family MRFs - Example: GLM Graphical Models (3)08:19
Exponential Family MRFs - Example: GLM Graphical Models (4)09:18
Learning Graphical Models09:47
Graphical Model Selection09:51
Neighborhood Estimation10:14
Statistical Guarantees10:45
Experiments - Simulated Data11:32
Experiments - Learning Genomic Network 112:25
Experiments - Learning Genomic Network 213:17
Summary13:47
Thank you!14:12