Official coursebook information
Lectures: Fri 13:15-15:00 in CO2
Exercises: Fri 15:15-17:00 in BC01
This course teaches an overview of modern mathematical optimization methods, for applications in machine learning and data science. In particular, scalability of algorithms to large datasets will be discussed in theory and in implementation.
- Instructors:
- Martin Jaggi [email protected]
- Nicolas Flammarion [email protected]
- Assistants:
- Aditya Varre [email protected]
- Amirkeivan Mohtashami [email protected]
- Yüksel Oguz Kaan [email protected]
- Chayti El Mahdi [email protected]
Contents:
Convexity, Gradient Methods, Proximal algorithms, Subgradient Methods, Stochastic and Online Variants of mentioned methods, Coordinate Descent, Frank-Wolfe, Accelerated Methods, Primal-Dual context and certificates, Lagrange and Fenchel Duality, Second-Order Methods including Quasi-Newton Methods, Derivative-Free Optimization.
Advanced Contents:
Parallel and Distributed Optimization Algorithms
Computational Trade-Offs (Time vs Data vs Accuracy), Lower Bounds
Non-Convex Optimization: Convergence to Critical Points, Alternating minimization, Neural network training
| Nr | Date | Topic | Materials | Exercises |
|---|---|---|---|---|
| 1 | 24.2. | Introduction, Convexity | notes, slides | lab01 |
| 2 | 3.3. | Gradient Descent | notes, slides | lab02 |
| 3 | 10.3. | Projected Gradient Descent | notes, slides | lab03 |
| 4 | 17.3. | Proximal and Subgradient Descent | notes, slides | lab04 |
| 5 | 24.3. | Stochastic Gradient Descent, Non-Convex Optimization | notes, slides | lab05 |
| 6 | 31.3. | Non-Convex Optimization | notes, slides | lab06 |
| . | 7.4. | easter vacation |
- | |
| . | 14.4. | easter vacation |
- | |
| 7 | 21.4. | Newton's Method & Quasi-Newton | notes, slides | lab07 |
| 8 | 28.4. | Coordinate Descent | notes, slides | lab08 |
| 9 | 5.5. | Frank-Wolfe | notes, slides | lab09 |
| 10 | 12.5. | Accelerated Gradient, Gradient-free, adaptive methods | notes, slides | lab10 |
| 11 | 19.5. | Mini-Project week |
- | |
| 12 | 26.5. | Opt for ML in Practice | notes, slides | Q&A |
| 13 | 2.6. | Opt for ML in Practice | notes, slides | Q&A Projects |
- Public playlist of 2021 videos (youtube)
- Playlist of 2022 videos (EPFL internal)
- Playlist of 2023 videos (EPFL internal)
The weekly exercises consist of a mix of theoretical and practical Python exercises for the corresponding topic each week (starting week 2). Solutions to exercises are available in the lab folder.
A mini-project will focus on the practical implementation: Here we encourage students to investigate the real-world performance of one of the studied optimization algorithms or variants, helping to provide solid empirical evidence for some behaviour aspects on a real machine-learning task. The project is mandatory and done in groups of 3 students. It will count 30% to the final grade. Project reports (3 page PDF) are due June 16th. Here is a detailed project description.
Final written exam on Monday 03.07.2023 from 15h15 to 18h15 (CO2, CO3). Format: Closed book. Theoretical questions similar to exercises. You are allowed to bring one cheat sheet (A4 size paper, both sides can be used). For practice:
- Convex Optimization: Algorithms and Complexity, by Sébastien Bubeck (free online)
- Convex Optimization, Stephen Boyd and Lieven Vandenberghe (free online)
- Introductory Lectures on Convex Optimization, Yurii Nesterov (free online)