Course on Optimal Transport in Generative Modeling
Syllabus
| Week | Date | Event | Links |
|---|---|---|---|
| 2 | 10.02.2026 | Lecture 1: Introduction to Optimal Transport (OT) | Slides |
| 2 | 12.02.2026 | Student Report №1 Topics Release | Page |
| 3 | 17.02.2026 | Lecture 2: Entropy-Regularized OT and Schrödinger Bridges | Slides |
| 3 | 19.02.2026 | Homework №1 Release | Page |
| 4 | 24.02.2026 | Student Report №1 | Page |
| 5 | 03.03.2026 | Homework №1 Q&A session | Page |
| 6 | 09.03.2026 | Student Report №2 Topics Release | Page |
| 7 | 17.03.2026 | Lecture 3: Schrödinger Bridges and ENOT | Slides |
| 7 | 18.03.2026 | Homework №1 Deadline | Page |
| 8 | 24.03.2026 | Lecture 4: Characterization of Schrödinger Bridges | Slides |
| 9 | 31.03.2026 | Student Report №2 | Page |
| 10 | 06.04.2026 | Homework №2 Release | Page |
| 10 | 07.04.2026 | Lecture 5: Schrödinger Bridge Matching | Slides |
| 10 | 08.04.2026 | Student Report №3 Topics Release | Page |
| 11 | 14.04.2026 | Lecture 6: Flow Models and Optimal Transport | Slides |
| 12 | 20.04.2026 | Homework №3 Release | Page |
| 12 | 21.04.2026 | Student Report №3 | Page |
| 13 | 27.04.2026 | Homework №2 Deadline | Page |
| 13 | 28.04.2026 | Homework №3 Q&A session | Page |
| 14 | 05.05.2026 | Project Defence | N/A |
| 15 | 11.05.2026 | Homework №3 Deadline | Page |
| 15 | 12.05.2026 | Final Exam | N/A |
Grading
The gradebook uses the following points and weights:
| Activity | Points | Weight |
|---|---|---|
| Homework 1 | 20 | 1.5 |
| Homework 2 | 20 | 1.5 |
| Homework 3 | 20 | 1 |
| Article report | 20 | 1 |
| Oral exam | 20 | 1 |
| Project | 30 | 1 |
The final score is
\[ \mathrm{Score} = 1.5(\mathrm{HW1} + \mathrm{HW2}) + \mathrm{HW3} + \mathrm{Report} + \mathrm{Exam} + \mathrm{Project}. \]
The maximum score is 150. The final grade is
\[ \min\left(\left\lfloor \frac{\mathrm{Score}}{10} \right\rfloor, 10\right). \]
Prerequisites
- Mathematics: Calculus, Probability Theory and Statistics, Linear Algebra, Optimization Methods
- Programming: Adequate Python programming skills, including familiarity with PyTorch
- Data Science: Basic knowledge of Algorithms, Machine Learning and Neural Networks
