Optimization for Data Science
-
Instructor: Yao-Liang Yu
-
Email: yaoliang.yu@uwaterloo.ca
Lectures (Tentative)
Topic | Slides | Notes | ||
00 | Introduction | |||
01 | Gradient Descent | |||
02 | Proximal Gradient | proj, prox | proj, prox | |
03 | Conditional Gradient | |||
04 | Subgradient | |||
05 | Mirror Descent | |||
06 | Metric Gradient | |||
07 | Accelerated Gradient | |||
08 | Minimax | |||
09 | Alternating | |||
10 | POCS | |||
11 | Splitting | |||
12 | Stochastic Gradient | |||
13 | Variance Reduction | |||
14 | Randomized Smoothing | |||
15 | ||||
16 | Newton | |||
17 | Riemannian Gradient | |||
18 | Adaptation | |||
19 | Perf Estimation | |||
Project
Project template: download zip; main file: project.tex; references: readings.bib
Textbook
There is no required textbook, but the following fine texts are recommended.
- Stephen J. Wright and Benjamin Recht. Optimization for Data Analysis. Cambridge University Press, 2022.
- Ernest K. Ryu and Wotao Yin. Large-Scale Convex Optimization. Cambridge University Press, 2023.
- Yurii E. Nesterov. Lectures on Convex Optimization. Springer, 2018.
- Boris T. Polyak. Introduction to Optimization. Optimization Software, 1987.