Foundations of Graphical Models
Fall 2015
Columbia University
Course information
- Description and Syllabus
- Instructor: David
M. Blei
- Teaching Assistant: Maja Rudolph
- Meeting: Mondays and Wednesdays, 1:10PM-2:25PM, 603 Hamilton
- Office hours for D. Blei: Wednesdays, 2:30PM-4:30PM, CEPSR 703
- Office hours for M. Rudolph: 3:30PM-4:30PM, Tuesdays (620 CEPSR)
and Thursdays (912 SSW)
- Piazza site
Course materials
Below are the readings and lecture notes. When available, we
include a link to the PDF of the readings. Otherwise, they are
available outside of Prof. Blei's office. The specific reading
assignments are announced on Piazza.
These topics may span multiple lectures in the class. See the
syllabus for the schedule. Note that these lecture notes are drafts
and works in progress. Feel free to email david.blei@columbia.edu
with comments and errors.
- Introduction
- A Quick Review of Probability
- Basics of Graphical
Models
- Reading: "Conditional Independence and Factorization" in
Introduction to Probabilistic Graphical Models (Jordan, 2003).
- Elimination, Tree Propagation, and the Hidden Markov Model
- Reading: "The Elimination Algorithm" in Introduction to
Probabilistic Graphical Models (Jordan, 2003)
- Reading: "Probability Propagation and Factor Graphs" in
Introduction to Probabilistic Graphical Models (Jordan, 2003)
- Models, data, and
statistical concepts
- Bayesian Mixture
Models and the Gibbs Sampler
- Probabilistic Modeling in Stan
- Exponential Families and Conjugate Priors
- Reading: "The Exponential Family" (Bishop, 2006; Section 2.4)
- Mixed-membership Models and Mean-Field Variational Inference
- Matrix Factorization and Recommendation Systems
- Generalized Linear Models
- Reading: "An outline of generalized linear models" in
Generalized Linear Models (McCullough and Nelder, 1989)
- Reading: "Multilevel linear structures" in Data Analysis Using Regression and Multilevel/Hierarchical Models
(Gelman and Hill, 2007)
- Reading: "Multilevel linear models: The basics" in Data Analysis Using Regression and Multilevel/Hierarchical Models
(Gelman and Hill, 2007)
- Regularized Regression
- Reading: The Elements of Statistical
Learning, Chapters 3.1, 3.2, 3.4, 3.6 (Hastie et al., 2009)
- Bayesian Nonparametric Models
Homework assignments
-
Homework 1
Out: 2015-09-30
Due: 2015-10-12
-
Homework 2
Out: 2015-10-20
Due: 2015-11-04
Other materials