The University of Texas at Austin
Department of Electrical and Computer Engineering

EE381V Statistical Machine Learning: Final Projects


Types of final projects (students may choose either one):



Project Proposal (Due: on 03/27/23, in class):



Evaluating final reports (the reports are due 04/24/23, 11:59pm):

  1. Research Paper

    (15 points) In the Introduction section, the article should provide background on the general area and motivate the research project.

    (10 points) In the Introduction (or a Problem Statement) section, clearly describe the objectives of the project. (Ideally, they should be very close to the objectives outlined in the project proposal.)

    (65 points) The main part of the paper should provide concise problem statement, setup, and key assumptions; description of methods (any derivations, algorithms employed, etc.); explanation of the project contributions illustrated with analytical and/or simulation results; and give some insight and provide suggestions for future work.

    (10 points) Since this is a report, please take care of clarity and style thereof. Please use 11pt or 12pt font (references may be 10pt), double spaced text, standard 1 inch margins. Preferred length (not including title, abstract, figures, and table-of-contents) is 10-12 pages. Alternatively, please

  2. Survey Article

    (15 points) In the Introduction section, the article should provide background on the general area and motivate the survey.

    (10 points) The references should be relevant to the topic of the survey. Journal papers are strongly preferred. Including references which present different approaches to the solution of the same problem is desirable.

    (65 points) The main part of the article -- survey of the area -- should provide details about the area/problem being surveyed; give a thorough description of the contributions in the cited papers; compare and contrast different contributions, including numerical/simulation illustrations; and give some insight and provide suggestions for future work.

    (10 points) Since this is a report, please take care of clarity and style thereof. Please use 11pt or 12pt font (references may be 10pt), double spaced text, standard 1 inch margins. Preferred length (not including title, abstract, figures, and table-of-contents) is 10-12 pages.


    Potential projects, with some interesting papers:

  1. Differential privacy in machine learning

  2. Robustness under adversarial attacks

  3. Bandit-aided boosting.

  4. PAC learnability of influence functions in social networks.

  5. Information-theoretic guarantees for ERM.

  6. Graph neural networks.

  7. Agnostic federated learning.

  8. Neural network pruning with performance guarantees.