11th Exercise, Optimization for Machine Learning, Sose 2023, LMU Munich

All teaching material is available at: [github](https://github.com/bengsV/OptML)

This video is the 11th exercise session for the Optimization for Machine Learning course (Summer Semester 2023) at LMU Munich, led by Viktor Bengs. In this session, a mock exam is discussed which covers most of the topics discussed in the course.

The session provides a comprehensive review to help students prepare for the final examination. Key topics revisited through the mock exam questions include:

*Fundamentals of Optimization:* Analysis of convex sets and functions.
*Gradient-Based Methods:* Discussion on Gradient Descent and its convergence properties.
*Stochastic Optimization:* Insights into Stochastic Gradient Descent (SGD) and its variants used in machine learning.
*Constrained Optimization:* Applying KKT conditions and understanding Lagrangian duality.
*Advanced Topics:* Brief look into proximal gradient methods and momentum-based acceleration.

Whether you are a student at LMU or a self-learner, this walkthrough serves as a summary of the mathematical foundations and algorithmic approaches in modern optimization for ML.

*Course:* Optimization for Machine Learning (Summer 2023)
*Institution:* Ludwig-Maximilians-Universität München (LMU)
*Instructor:* Viktor Bengs

[   • 11th Exercise, Optimization for Machine Le...  ](https://www.google.com/search?q=https...)