Mathematical Algorithmic Optimization - Otto-von-Guericke-University Magdeburg

 
 
 
 
 
 
 
 

Lecture: Optimization Methods for Machine Learning

The lecture (LSF) will be taught in English and addresses Master and PhD students in Mathematics or related fields. We will use a virtual format, with videos of the lectures that can be asynchronically assessed and online practical exercises and discussions using Zoom.

Registration and first (virtual) meeting

The lecture and exercises time slots have now been allocated (LSF). We are going to have a first virtual Zoom meeting on Tuesday, October 27, 13:15. Use the password 2020omml to enter. In this first meeting all organizational questions will be discussed, among others which of the two available time slots on Thursday shall be used for the practical exercises.

You do not need to register officially, but it would be helpful if you could send an email to specifying your name, your curriculum (Master, PhD in ...), your Immatrikulationsnummer, and your email, this would be very helpful to set up invitations to MatterMost and to a computing server. Please send this email before October 26.

Exercises and Downloads

On this password-protected page

Information
Content

It will survey optimization problems in and methods for machine learning.

A preliminary table of contents is the following.

Practical exercises will complement the lecture and focus on KERAS and Python scikit-learn.

Requirements

Mathematical basics (Analysis and Linear Algebra) and programming skills. Introduction to Optimization. The lecture Nonlinear Optimization is highly recommended, but not absolutely necessary.

Module description
The lecture is a master lecture in the mathematics curriculum and described in the module handbook (currently page 31) as a Wahlpflicht module: A translation of the module description:

The lecture is also open to other master and PhD students of OVGU. In particular, there is an agreement that ORBA students may choose the lecture as a Wahlpflicht (with 10 CP to motivate the independent study of mathematical foundations necessary to follow the lecture). However, please note that the lecture is addressed to mathematical master students and assumes a good understanding of mathematical basics, especially in the second part of the lecture. If you are mainly interested in applying machine learning and not so much in analyzing the training process, other lectures might be better suited for you. Note that the lecture Concepts and Algorithms of Optimization is not sufficient as a requirement, you will have to invest more time to acquire additional mathematical knowledge.

Questions?

Feel free to send me an email with general questions:

Last Modification: 2020-10-22 - Contact Person: Sebastian Sager - Impressum