CS 228T: Advanced Topics in Probabilistic Graphical Models
This is an archive of materials used for CS 228T, taught at Stanford in 2011 with Daphne Koller.
An advanced course on probabilistic graphical models, covering advanced MCMC methods, variational inference, large margin methods, nonparametric Bayes, and other topics.
The course requires CS 228 (probabilistic graphical models); CS 229 (machine learning) and EE 364A (convex optimization) are recommended.
- Advanced MCMC methods
- Variational inference
- MAP estimation
- Large margin methods
- Structure learning
- Latent variable models and topic models
- Bayesian nonparametrics
The syllabus may be adjusted through the course of the semester.
The textbook is Koller and Friedman, Probabilistic Graphical Models, and various research papers will be assigned throughout the semester.