STAT424 | Optimization for Statistical Learning
Spring 2022
Time: Tu/F 1:00-2:30pm in Microsoft Teams
Instructor
-
Donlapark Ponnoprat
Office: STB304
References
- Amir Ali Ahmadi, Computing and Optimization (ORF 363) Lecture Notes.
- Boyd and Vandenberghe, Convex Optimization (2014) book.
- David Childers, Forecasting for Economics and Business (73-423) Lecture Notes.
- Julian McAuley, Personalized Machine Learning (2022) book draft.
Lecture Notes
No. | Topic | Slides |
---|---|---|
1 | Some games and motivation | Lecture 1 |
2 | Linear algebra & calculus review 1 | Lecture 2 notebook |
3 | Linear algebra & calculus review 2 | Lecture 3 |
4 | Unconstrained optimization | Lecture 4 |
5 | First & second order optimization, convex sets | Lecture 5 |
6 | Convex functions | Lecture 6 |
7 | Convex optimization | Lecture 7 notebook |
8 | Applications of convex optimization | Lecture 8 |
9 | Bisection, Newton, and secant methods | Lecture 9 |
10 | Gradient descent methods | Lecture 10 |
11 | Multivariate Newton and the Gauss-Newton algorithm | Lecture 11 |
12 | Conjugate direction methods | Lecture 12 |
13 | Linear programming | Lecture 13 |
14 | Geometry and simplex method | Lecture 14 |
15 | Duality | Lecture 15 |
16 | Applications of linear programs and duality | Lecture 16 |
17 | Linear programs in game theory | Lecture 17 |
18 | Constrained convex optimization, Frank-Wolfe algorithm | Lecture 18 |
19 | Regularization, Sparsity and energy minimization | Lecture 19 |
20 | Online convex optimization I | Lecture 20 |
21 | Online convex optimization II | Lecture 21 |
22 | Nonconvex optimization: neural networks and recommender systems | Lecture 22 |