# | Date | Topic | Notes | Lecture | Notebook |
---|---|---|---|---|---|
Part I: Basic gradient methods | |||||
1 | 08.(23/25) | Intro & Preliminaries | .ipynb .ipynb | ||
2 | 08.30-09.(01/06) | Gradient method | .ipynb | ||
3 | 09.(08/13/15) | Gradient method & Convexity | .ipynb | ||
4 | 09.(20/22/27) | Conditional gradient (Frank-Wolfe) | .ipynb | ||
Part II: Going faster than basic gradient descent | |||||
5 | 09.29-10.04 | Beyond first-order methods | .ipynb | ||
6 | 10.(06/13) | Momemtum acceleration | .ipynb | ||
7 | 10.(18/20) | Stochastic motions in gradient descent | .ipynb | ||
Part III: Provable non-convex optimization | |||||
8 | 10.(25/27)-11.01 | Sparse feature selection and recovery | .ipynb | ||
9 | 11.(03/08) | Low-rank recovery | .ipynb | ||
Part IV: Optimization methods in modern ML | |||||
10 | 11.(17/22) | Landscape properties of general functions | — | ||
11 | 11.(22) | Distributed computing + Algorithms for NN training | /schedule/images/chapter11-12.pdf | .pdf/.pdf | — |
13 | 11.29-12.01 | Project presentations | — | — | — |
Part V: Final exam |