Lecture Materials

The course contains eleven content lectures and two student-presentation sessions.

For each lecture, this section provides or reserves a place for:

• the Learning Sheet or presentation brief;
• a Validation Sheet and released solutions;
• a Cheatsheet for each content lecture in Lectures 1–11;
• Tutorial notes and worked discussions;
• the relevant Part Test when scheduled.

Part 1 · Mathematical Preliminaries

• Lecture 1: Mathematics Part A
• Lecture 2: Mathematics Part B

Part 2 · PAC Learning Framework

• Lecture 3: PAC Learning and VC Dimension
• Lecture 4: PAC Learning and VC Dimension
• Lecture 5: Agnostic Learning and Complexity

Part 3 · Classical Methods

• Lecture 6: Regularization
• Lecture 7: Model Selection

Part 4 · Ensemble Learning

• Lecture 8: AdaBoost
• Lecture 9: Margins and Loss Minimization

Part 5 · Online Learning

• Lecture 10: Expert Advice and MWU
• Lecture 11: Online Convex Optimization

Validation Sheets and Solutions

Released solutions include the questions and worked answers. Question-only sheets for other lectures are available on their individual lecture pages.

Lecture	Questions only	With solutions
Lecture 1	📝 Questions (PDF)	📖 Solutions (PDF)
Lecture 2	📝 Questions (PDF)	📖 Solutions (PDF)
Lecture 3	📝 Questions (PDF)	📖 Solutions (PDF)
Lecture 4	📝 Questions (PDF)	📖 Solutions (PDF)
Lecture 5	📝 Questions (PDF)	📖 Solutions (PDF)

Tutorial Notes

• Tutorial 1: Expectation, Bounds, and Covariance
• Tutorial 2: Coordinates, Gradient Descent, and SOAP

Student Presentations

The presentations are based on each student's individual Market Lab project.

• Lecture 12: Student Presentations I
• Lecture 13: Student Presentations II