Probabilistic Graphical Models

Denis Deratani Mauá


These are the lecture notes of the Graduate Course MAC6916 Probabilistic Graphical Models, taught within the Computer Science Program of the Institute of Mathematics & Statistics since 2016. These notes are preliminary and in constant change (use at your own risk ☺). Comments and error reports are very welcome.

  1. Preamble: Introduction to Probabilistic Graphical Reasoning
  2. Probability Theory
  3. Bayesian Networks
  4. Representing Independences
  5. Missingness Graphs
  6. Markov Equivalence
  7. Markov Networks
  8. Constraint-Based Structure Learning
  9. Parameter Learning
  10. Score-Based Structure Learning
  11. Probabilistic Inference By Sampling
  12. Variable Elimination
  13. Sum-Product Algorithms
  14. Bayesian Networks Classifiers
  15. Causality