The general aim is that the student gains knowledge about the recent developments in the area of statistics. At the end of the course, the student
- is able to explain recent methodological and theoretical developments in statistical learning, including where and how these methods are used.
- is able to read recent research papers and grasp the material in such a way that
(i) the student can present it to the fellow students and
(ii) the student can indicate the most important aspects of the paper by formulating suitable questions/assignments (for the fellow students) and subsequently grading them appropriately.
The aim of this course is to get advanced knowledge of some of the contemporary research topics in the area of Statistical Learning and Optimization. The course can cover topics such as PAC Learning, linear classifiers, support vector machines, regularization and kernel methods; these models and theory will then further be enriched by the study of recent stochastic optimization methods, including (stochastic) first-order methods, proximal algorithms, composite minimization, variational inequalities and saddle point problems, and variance-reduction methods. The specific topics may vary each year, and the background material for this course will be selected from recent books and papers on the relevant topics. Essential for this course is an active participation of the students. In particular, the students give part of the lectures and receive comments.|
After a first introduction, the available topics for lectures are presented and distributed. Student lecturtes are either an individual assignment or done in pairs, depending on the number of students. Students will get support from the instructors in preparing their presentations for the course. Besides presenting a particular topic, the presenter(s) will setup an assignment on the topic that will be solved by the fellow students. These assignments are graded by both the teacher and the student(s) who gave the lecture. The final grade is composed of the quality of the students’ presentation (60%), the overall participation during the course (10%), and the average score for the assignments (30%).