Optimization for Machine Learning

Below you can find slides and lecture notes. The syllabus can be found here, the homework here and the projects here.

Lecture 1 slides, Lecture notes: Definitions and Gradient Descent
Lecture 2 slides, Lecture notes: Stochastic Gradient Descent
Lecture 3 slides: Stochastic Gradient Descent (part 2)
Lecture 4 slides, Lecture notes: Online optimization and Online Learning
Lecture 5 slides, Lecture notes: Non-convex optimization
Lecture 6 slides: Non-convex optimization (part 2)
Lecture 7 slides, Lecture notes: Accelerated GD (Nesterov)
Lecture 8 slides, Lecture notes: Intro to min-max optimization
Lecture 9 slides: Min-max optimization using optimism
Lecture 10 slides, Lecture notes: Intro to statistical learning and ERM
Lecture 11 slides: VC dimension
Lecture 12 slides, Lecture notes: Intro to multi-armed bandits
Lecture 13 slides: Intro to multi-armed bandits part 2
Lecture 14 slides: Intro to MDPs