MA3K1 - Lecture Notes

The lecture notes will usually appear before the relevant week and updated after it. At the end of the course, a complete set of notes will be made available. The lecture video recording is also available here.

Overview of Mathematical Background [PDF]
Overview of Probability Theory and Statistics [PDF]
Preliminary Table of Contents [PDF]
Lecture 1 - Introduction [PDF] [Intro Slides] [Video]
Lecture 2 - Binary Classification [PDF] [Slides] [Video]
Lecture 3 - Concentration of Measure [PDF] [Slides] [Video]
Lecture 4 - The Bias-Variance Tradeoff [PDF] [Slides] [Video]
Lecture 5 - Finite Hypothesis Sets [PDF] [Slides] [Video]
Lecture 6 - Probably Approximately Correct [PDF] [Slides] [Video]
Lecture 7 - Rademacher Complexity [PDF] [Slides] [Video]
Lecture 8 - VC Theory [PDF] [Slides] [Video]
Lecture 9 - Review and Examples [Slides] [Supplementary material] [Video]
Lecture 10 - Model Selection [PDF] [Slides] [Video] [Code]
Lecture 11 - Overview of Optimization [PDF] [Slides] [Video] [Code]
Lecture 12 - Convexity [PDF] [Slides] [Video]
Lecture 13 - Lagrangian Duality [PDF] [Slides] [Video]
Lecture 14 - KKT Optimality Conditions [PDF] [Slides] [Video]
Lecture 15 - Support Vector Machines [PDF] [Slides] [Video]
Lecture 16 - Iterative Algorithms [PDF] [Slides] [Video]
Lecture 17 - Gradient Descent [PDF] [Slides] [Video]
Lecture 18 - Stochastic Gradient Descent [PDF] [Slides] [Video]