Combinatorial Optimization in Machine Learning and Computer Vision

Dr. Bogdan Savchynskyy, Prof. Dr. Carsten Rother, WiSe 2020/21

This seminar belongs to the Master in Physics (specialisation Computational Physics, code "MVJC"), Master of Applied Informatics (code "IS") as well as Master Mathematics (code "MS") programs, but is also open for students of Scientific Computing and anyone interested.


Machine learning techniques are tightly coupled with optimization methods. Many techniques become practical only if there exists a supporting optimization tool.

In the seminar we will discuss a number of recent articles on combinatorial optimization with applications in computer vision and machine learning.

The topic of this semester is

Neural Networks meet Combinatorial Optimization

In particular, we will consider methods for

  • training parameters of combinatorial optimization algorithms with the machine learning techniques,
  • combinatorial optimization based loss-functions for deep learning
and their applications.

General Information

Please register for the seminar in Müsli. The seminar will be held online in MS Teams, all links will be send per email via Müsli.
Attention: To be able to join the seminar online you must enable MS Teams here. Please do it ASAP, your request may take several days.
The first seminar will take place on Wednesday, November 4 at 16:00. Please make sure to participate!

  • Seminar: Wed, 16:00 – 18:00
  • Credits: 2 / 4 / 6 CP depending on course of study

Papers and Organizatory Information

Will be uploaded here. The password was sent via email.


See seminar-plan.txt in HeiBox.


Dr. Bogdan Savchynskyy