High-dimensional Statistics II


Email the Professor to obtain access to the most updated version of the script.

Time and location

Note the change of location!
Tu, 2pm–4pm, IA 1/181
Th, 2pm–4pm, IA 1/95

Course Schedule

It is expected that you have studied the topics before the corresponding lecture. Exercises marked by a bullet will be presented by me; the other exercises will be presented by you.

Date Topics Homework due
April 2 course introduction
April 4 self study (no class)
April 9 linear regression+Section 2.2+Exercise 2.2 Exercise 2.2
April 11 External presentation (Julien Bodelet)
April 16 Section 2.3+Exercise 2.3
April 18 Exercises 2.4–2.6 Exercises 2.4–2.7
April 23 Exercises 2.7–2.9
April 25 External presentation (Prof. Hebiri)
April 30 Section 6.1+Section 6.2 first-order OI
May 2 Section 6.2 second-order OI+Exercise 6.1
May 7 discussion class if needed (Fang)
May 9 discussion class if needed (Fang)
May 14 Section 6.3 first part
May 16 Section 6.3 second part+Exercise 6.2
May 21 Exercises 6.3–6.4 Exercises 6.3–6.4
May 23 Section 6.4 first part
May 28 Section 6.4 second part+Exercise 6.5 Exercise 6.6
May 30 holiday (no class)
June 4 Section 6.5 first part
June 6 self study Section 6.5–6.6 (no class)
June 11 holiday (no class)
June 13 holiday (no class)
June 18 Exercises 6.6–6.9 Exercises 6.8–6.10
June 20 holiday (no class)
June 25 Sections 7.1–7.2+Exercise 7.1 (Fang)
June 27 Section 7.3 (Fang)
July 2 Exercises 7.2–7.7
July 4 Section 7.4
July 9 TBD
July 11 TBD

Taking Notes

The script will be updated from time to time. Unfortunately, as pointed out in last semester’s course evaluation, this means that any electronic notes attached to the script will be lost. I would, therefore, suggest to take handwritten notes. However, if you have a better idea, please let me know!

Additional Files

An additional data example for Section 1.1
Code for Exercise 1.7, Claim 11
Data for the lab in Section 3
Slides for Section 4.5


We expect active participation in the lectures. This includes you having read the materials prior to the lectures and being part of the discussions in class.




Send feedback to datascience@rub.de or through the anonymous feedback form.