6FMAI19 Lectures
What we plan to cover:
- Gradient descent
- Proximal point algorithm
- Constrained optimization
- Accelerated methods
- Subgradient methods
- Stochastic gradient method
- Mirror descent
- Primal-dual methods
- Variational inequalities
- Second-order methods
- Various applications
Date | Lecture | Scribe | Homework |
---|---|---|---|
19.01.22 | Lecture 1. Introduction | --- | --- |
26.01.22 | Lecture 2. Convexity. Optimality condition | lecture-2.pdf | |
2.02.22 | Lecture 3. L-smooth functions. Gradient descent | lecture-3.pdf | assignment-1.pdf |
9.02.22 | Lecture 4. GD for convex functions. Constrained Optimization | lecture-4.pdf | |
16.02.22 | Lecture 5. Projected Gradient Method. Subgradient | lecture-5.pdf | |
23.02.22 | Lecture 6. Projected Subgradient Method | lecture-6.pdf | |
2.03.22 | Lecture 7. Empirical Risk Minimization Problem. Stochastic Subgradient Method | ||
9.02.22 | Lecture 8. Stochastic Gradient Method | lecture-8.pdf | assignment-2.pdf |
23.03.22 | Lecture 9. Exercises + Subgradient method for strongly convex case | lecture-9.pdf | |
30.03.22 | Lecture 10. Proximal point algorithm | lecture-10.pdf | |
6.04.22 | Lecture 11. Duality | ||
13.04.22 | Lecture 12. Smoothness and strong convexity | lecture-12.pdf | |
20.04.22 | Lecture 13. Using duality in practice | lecture-13.pdf |
Template for scribing lectures: template.tex
Sidansvarig: webmaster@mai.liu.se
Senast uppdaterad: 2022-04-29