Discrete Optimization and Machine Learning
Sebastian Pokutta (SoSe 2020 / Seminar)
Sebastian Pokutta (SoSe 2020 / Seminar)
Both Machine Learning methods as well as Discrete Optimization methods are important tools in many real-world applications. In this course we will primarily study the interplay of integer programming and, more broadly, discrete optimization methods and machine learning. We will cover, among other things:
The format of the course is strongly research-oriented requiring active participation of the students. The course will be a mix of traditional lectures, student presentation, discussions, and project work. In the first few weeks in-class projects will be defined.
Coordinates:
Time: TBA
Room: TBA at TU Berlin
Prerequisites: Linear Algebra, Analysis, and Discrete Optimization (ADM I/ADM II)
Office hours: by appointment
Reading material by topic:
Boosting and LP-Boost:
Reinforcement Learning:
Online Convex Optimization:
Submodular Function Maximization:
Machine Learning for solving Integer Programs:
Online Submodular Function Maximization:
Online Learning:
Sparse Regression:
Inverse Reinforcement Learning:
Experience Relay:
Conditional Gradients:
Adversarial Learning: