FRTN50 - Optimization for Learning
Course Program
The course program contains the schedule and all relevant information regarding lectures, exercises, content, logistics, deadlines etc. The course program and other course material will be updated when needed.
Covid-19 Policy
Our policy is based on our department's general guidelines . The policy can be found in the course program.
Zoom Meeting Invites
See the following Announcement .
Lecture Videos
Some lecture videos (that are short flipped classroom type videos, not lecture recordings) can be found here.
Intended use: The videos are intended for active listening. This means pausing, skipping 15 s back (or forward) within video to repeat, e.g., an argument, skipping between videos to recall concepts, changing playback speed, and maybe taking notes and verifying calculations while watching.
Lecture videos for the remaining lectures are recorded during live Zoom presentations and can be found here.
Lecture Slides
- Intro
- L1 - Convex sets (videos)
- L2 - Convex functions (videos)
- L3 - Subdifferentials and the proximal operator (videos/videos)
- L4 - Conjugate functions and duality (videos/videos)
- L5 - Proximal gradient method - Basics (videos)
- L6 - Least squares (video)
- L7 - Logistic regression (video)
- L8 - Support vector machines (video)
- L9 - Deep learning (video)
- L10 - Convergence rates and proving convergence (videos)
- L11 - Proximal gradient method - Theory (videos)
- L12 - Stochastic gradient descent (videos)
- L13 - Coordinate gradient descent (unfortunately forgot to record Zoom lecture)
- Bonus - Newton's method and quasi-Newton methods
- Bonus - Implicit regularization
- Recap
Exercise Material
- Exercise Compendium (updated: 20-10-07)
- Introduction to Julia