Statistical Learning

Prof. Dr. Christian Bender

Winter Semester 2024/2025

Recommended prerequisites

Knowledge of measure-theoretic probability theory at the level of the mathematics course Stochastik I.

Lectures

Thursdays, 12.15 - 13.45 pm, 
building E2 4, HS IV (room 1.15)

Tutorials

One hour per week (by arrangement)

Exam

Oral exam at the end of the semester.

Course material

The course material can be found on the learning management system Moodle. If you are interested to attend the course, please ask for the enrolment key at your earliest convenience via email to:

bender [at] math.uni-sb.de

Moodle enrolment
 

Contents

  • Introduction to the regression problem and to pattern recognition
  • Local averaging methods (e.g., kernel smoothing, k-nearest neighbor) 
  • Concentration inequalities (Hoeffding, Bernstein)
  • Sample splitting
  • Empirical risk minimization
  • Vapnik-Chervonenkis inequality
  • Combinatorial aspects of the Vapnik-Chervonenkis theory