Kernel Methods and Applications

Reproducing kernels provide a powerful modelling and approximation framework, which have been widely applied to problems in science and technology. Rooted in functional analysis and approximation theory, kernels lead to a theoretical framework of surprising mathematical elegance on one hand, and to simple and robust algorithms on the other hand. In this course, we will learn about both theory and applications of kernel methods. Practical coding exercises will accompany the course.

Literature

Steinwart / Christmann, Support Vector Machines, Springer 2008
Wendland, Scattered Data Approximation, Cambridge 2005
I will also provide lecture notes which I'll keep updating over the course of the semester.

Dates

Class: Thursday 10-12, A6 / SR032
Exercise: Thursday 12-14, A14 1.4.03 (Physics Department)
For the tutorials, please bring your own laptop if possible.

Zoom Links:

Classes: 
https://eu02web.zoom-x.de/j/67696304106?pwd=M211dTY3QlYvdVVabFN0R1hGU2Rrdz09

Course Requirements:

- active participation: in each tutorial, we'll work on a provided problem set. Students can work on it during the tutorials, even in groups. Students need to submit their solution through the whiteboard page until the evening of the next day. Active participation requires submitting a reasonable solution to at least half of the problems.

- exam: we'll have a written exam on July 18, 10-12.

Specific Dates:
18/04/24: no exercise, online class 12-14
09/05/24: public holiday
16/05/24: no exercise, online class 14-16
23/05/24: no classes
13/06/24: no classes
04/07/24: no exercise, online class 10-12

Contact

preferably by email: nueske@mpi-magdeburg.mpg.de
 

Zusätzliche Informationen

Zielgruppe: Studierende der Masterprogramme Mathematik, Informatik, Computational Sciences und Data Science.