2023/2024

Optimization in Machine Learning

Type: Optional course (faculty)

Delivered by: Big Data and Information Retrieval School

When: 1, 2 module

Online hours: 52

Open to: students of one campus

Language: English

ECTS credits: 6

Contact hours: 10

Course Syllabus

Abstract

Optimization methods are the basis for solving many problems in computer science. For example, in machine learning, the optimization problem must be solved every time you configure some model of algorithms based on data. Moreover, the practical applicability of the machine learning method itself depends on the effectiveness of solving the corresponding optimization problem. This course is devoted to the study of classical and modern methods for solving continuous optimization problems (including non-convex), as well as the features of using these methods in optimization problems that arise in machine learning. The main emphasis in the materials is on the practical aspects of the implementation and use of methods. By the beginning of the course, students are required to have a basic knowledge of linear algebra. Students’ academic performance is evaluated using programming assignments, theoretical homework and scientific experiments with the final report.