194.109 Machine Learning Theory Project
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2021W, PR, 2.0h, 3.0EC


  • Semester hours: 2.0
  • Credits: 3.0
  • Type: PR Project
  • Format: Distance Learning

Learning outcomes

After successful completion of the course, students are able to...

  • summarize and present theoretical properties of a machine learning algorithm;
  • identify theoretical weak points of a learning algorithm;
  • independently study and solve specific theoretical problems;
  • apply theoretical results;
  • check assumptions made by the algorithms.

Subject of course

In this machine learning theory project, the students will be working on specific theoretical research questions in the area of machine learning. During the semester the students will prove theoretical statements in a chosen area of machine learning. Expected results include for example:

  • Formal guarantees for a certain learning algorithm, like sample, query or computational complexity bounds.
  • Worst-case instances where the algorithm in question provably performs badly.
  • Formalization of underlying assumptions of an algorithm.

Teaching methods

Students read original papers and perform literature research for related work. They work on novel theoretical guarantees, present their results online, and write a project report.

Mode of examination


Additional information

3ects -> 75h
8h literature search and proposal writing
12h preparing and attending presentations and project meetings
42h formal proofs, implementation, and testing
13h writing the project report



Examination modalities

The final grade is made up of the quality of

  • the developed theoretical results,
  • the online presentations, and
  • the submitted written report.

Course registration

Begin End Deregistration end
01.09.2021 00:00 14.11.2021 23:59



No lecture notes are available.

Accompanying courses