Dr. Rina Dechter - University of California at Irvine ZOT!
home | publications | book | courses | research Revised on Apr. 18, 2018

CompSci-276 Spring 2018, Reasoning in Graphical Models
[ main | software | references ]


Course Reference

    Lecture
    Days: Monday/Wednesday
    Time: 11:00 am - 12:20 pm
    Room: ICS 180

    Instructor: Rina Dechter
    Office hours: Monday 4:00 pm - 5:00 pm

Course Description

The objective of this class is to provide an in-depth exposition of representation and reasoning under uncertainty using the framework of Graphical models. The class focuses on reasoning with uncertainty using directed and undirected graphical models such as Bayesian networks, Markov networks and constraint networks. These graphical models encode knowledge as probabilistic relations among variables. The primary reasoning tasks are, given some observations, to find the most likely scenario over a subset of propositions, or to update the degree of belief (distribution) over a subset of the variables. The primary algorithms (exact and approximate) using variational message-passing, search and sampling will be covered, with illustrations from areas such as bioinformatics, diagnosis and planning. Additional topics may include: causal networks, and dynamic decision networks (Influence diagrams and MDPS), as time permits.

Prerequisites

  • Familiarity with basic concepts of probability theory.
  • Knowledge of basic computer science, algorithms and programming principles.
  • Previous exposure to AI is desirable but not essential.

Course material

The course will be based mostly on four sources:

Additional sources:

A longer list including secondary references.

Some links to software and tools.

Syllabus

Week       Date Topic Readings           Slides        
Week 1 4/2
  • Introduction: Constraint and probabilistic graphical models
Dechter1 ch. 1-2
slides 1
  4/4
  • The constraint network model: Graphs, modeling, Inference
slides 2
hw 1
Week 2 4/9
  • Inference in constraints: Adaptive consistency, constraint propagation, arc-conistency
  • Lecture 3
Dechter1 ch. 2-3
Dechter2 ch. 3-4
  4/11
  • Graph properties: induced-width, tree-width, chordal graphs, hypertrees, join-trees
  • Lecture 4
Week 3 4/16
  • Bayesian and Markov networks: Representing independencies by graphs
  • Lecture 5
slides 3
  4/18
Week 4 4/23
  • Probabilistic Inference: Bucket-elimination (summation and optimization)

4/25

Week 5 4/30
  • Probabilistic Inference: Tree-decompositions, Join-tree/Junction-tree algorithm


5/2
  • Bounded Inference: weighted Mini-bucket, belief-propagation,
    generalized belief propagation, variational, cost-shifting methods)
Week 6 5/7
  • Search: Backtracking search in CSPs; pruning by constraint propagation,
    backjumping and learning

5/9
  • Search: AND/OR search Spaces for likelihood, optimization queries
    (Probability of evidence, Partition function, MAP and MPE queries)
Week 7 5/14
  • Sampling: Gibbs sampling, Importance sampling, cutset-sampling,
    SampleSearch and AND/OR sampling, Stochastic Local Search


5/16
Week 8 5/21
  • Mixed queries: (Influence diagrams, marginal map, mixture of constraints and probabilities)

5/23
  • No class

Week 9 5/28
  • Memorial Day - No class

5/30
  • Causal Inference in Statistics

Week 10 6/4



6/6
  • Project presentations


Week 11 6/11
  • Project presentations



Assignments:

There will be homework assignments and students will also be engaged in projects.

Grading Policy:

Homework and exam (70%), class project (30%)