Official coursebook information
Lectures: Fri 13:15-15:00 in CE2
Exercises: Fri 15:15-17:00 in CE2
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.
- Instructor: Martin Jaggi [email protected]
- Assistants:
- Prakhar Gupta [email protected]
- Sai Praneeth Karimireddy [email protected]
- El Mahdi El Mhamdi [email protected]
- Nicolas El Maalouly [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, Synchronous and Asynchronous Communication.
Computational and Statistical Trade-Offs (Time vs Data vs Accuracy). Variance Reduced Methods, and Lower Bounds.
Non-Convex Optimization: Convergence to Critical Points, Saddle-Point methods, Alternating minimization for matrix and tensor factorizations
| Nr | Date | Topic | Materials | Exercises |
|---|---|---|---|---|
| #1 | 23.2. | Introduction, Convexity | notes, slides | lab01 |
| #2 | 2.3. | Gradient Descent | notes, slides | lab02 |
| #3 | 9.3. | Projected Gradient Descent | notes, slides | lab03 |
| #4 | 16.3. | Proximal, Subgradient and Stochastic Gradient | notes, slides | lab04 |
| #5 | 23.3. | Stochastic Gradient Descent | ||
| . | 30.3. | easter vacation |
- | |
| . | 6.4. | easter vacation |
- | |
| #6 | 13.4. | |||
| #7 | 20.4. | |||
| #8 | 27.4. | |||
| #9 | 4.5. | |||
| #10 | 11.5. | Mini-Project week |
||
| #11 | 18.5. | |||
| #12 | 25.5. | |||
| #13 | 1.6. |
The weekly exercises consist of a mix of theoretical and practical Python exercises for the corresponding topic each week (starting week 2). Additionally, the 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. Project is done individually, not graded, and collaboration is encouraged.
Final written exam in exam session. Format: Closed book. Theoretical questions similar to exercises. You are allowed to bring one cheat sheet (A4 size paper, both sides can be used), either handwritten or 11 point minimum font size.
- 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)