Probabilistic Graphical Models

10-708, Spring 2021
School of Computer Science
Carnegie Mellon University


Assignments

There will be 5 homework assignments during the semester. The assignments will consist of both theoretical and programming problems. Homework assignments will be released via a Piazza announcement explaining where to find the handout, starter code, LaTeX template, etc.

  • Homework 1: Properties of Graphical Models (written)
    [Handout]
  • Homework 2: General-graph CRF Module for PyTorch [natural language processing] (written / programming)
    [Handout]
  • Homework 3: Structured SVM [computer vision] (written / programming)
    [Handout]
  • Homework 4: Gibbs Sampling [topic modeling] (written / programming)
    [Handout]
  • Homework 5: Variational Inference (written / programming) [Handout]

Tentative release dates and due dates are listed on the Schedule page.

Project

The course project affords an opportunity to explore an interesting problem in your domain of interest. Crucially, the project must employ graphical models for a structured prediction task or latent variable modeling. Students will submit several deliverables throughout the semester. The (tentative) deadlines for each component of the project are listed on the Schedule page.

  1. Team Formation: Each team will consist of 3-4 people. Teams must be specified in advance of the proposal deadline.
  2. Proposal: The proposal will describe the task, dataset, and methods.
  3. Midway Poster: The midway poster offers each group a chance to present their progress halfway through the project’s duration. The methods section should be (nearly) in its final form. The experiments section should minimally include a description of the experiments that will be run. Skeleton tables and plots without actual numbers are encouraged. Any results that are ready may also be reported. Students are required to attend the midway poster session.
  4. Midway Executive Summary: The midway executive summary offers each group a chance to present their progress halfway through the project’s duration. The methods section should be (nearly) in its final form. The experiments section should minimally include a description of the experiments that will be run. Skeleton tables and plots without actual numbers are encouraged. Any results that are ready may also be reported. (If a midway poster session is held, students are required to attend.)
  5. Final Poster: The final poster should summarize the accomplishments of the project. (Students are required to attend the final poster session.)
  6. Final Executive Summary: The final executive summary should describe the methods that were used and the present experimental results that illustrate a contrast between competing methods.

Details about the project milestones and deliverables can be found here:
[Handout]