Bavarian AI Chair for Mathematical Foundations of Artificial Intelligence

Breadcrumb Navigation


High Dimensional Probability

Course Description

Randomness is critical to our society, and its ubiquitous influence has been growing as our technology advances. Hence, it is crucial to understand its underlying property, and such knowledge can be used in many application, such as reconstructing signals and developing efficient algorithms. This course provides a fundamental mathematical toolbox for analyzing problems in high dimensions, including but no limited to concentration inequalities on random vectors and matrices, as well as proof techniques such as covering arguments, decoupling, and symmetrization.


Participants are expected to have knowledge of basic probability (WP3 Stochastics). Additional knowledge of advanced probability and analysis (WP20 Probability Theory) is also highly recommended.

Schedule and Venue

Lectures: Mon 14:00–16:00 (B 047) & Tue 12:00–14:00 (B 047)

There are two slots for the exercise session. You should only attend one slot (A or B).

Exercise Class A: Fr 10:00-12:00 (A 027)

Exercise Class B: Fri 12:00–14:00 (B 132) 

Creditable Modules

  • Master in Mathematics: WP35 Fortgeschrittene Themen aus der künstlichen Intelligenz und Data Science (9 ECTS)
  • Master in Mathematics: WP27 Fortgeschrittene Themen aus der Stochastik (9 ECTS)
  • Master in Financial and Insurance Mathematics: WP13 Advanced Topics in Mathematics A (9 ECTS)


Please register on uni2work ( Make sure you register for one of the two exercise sessions.