Lectures :

1. Lecture 1: Introduction, course details, A Bit of Fun [Notes]
   [Course Logistics Info]
   Reference : [1] (ch 2)

2. Lecture 2: Bit Prediction, Cover's Lemma [Notes]
   Reference : [1] (ch 2)

3. Lecture 3: Cover's Lemma, Rademacher Complexity and Betting Problem [Notes]
   Reference : [1] (ch 2)

4. Lecture 4: Learning Frameworks [Notes]

5. Lecture 5: Minimax Value, Statistical Learning, Uniform Convergence [Notes]

6. Lecture 6: Uniform Convergence, Rademacher Complexity and Infinite Classes [Notes]

7. Lecture 7: Massart's Finite Lemma, Growth Function, Binary Classification and VC Dimension [Notes]

8. Lecture 8: Properties of Rademacher Complexity [Notes]

9. Lecture 9: Properties of Rademacher Complexity, Examples and Covering Number [Notes]

10. Lecture 10: Covering Numbers, Pollard Bound and Dudley Chaining [Notes]

11. Lecture 11: Wrapping Up Statistical Learning [Notes]

12. Lecture 12: Online Convex Optimization [Notes]

13. Lecture 13: Online Mirror Descent [Notes]

14. Lecture 14: Online Mirror Descent Faster Rates [Notes]

15. Lecture 15: Online Linear Bandits [Notes]

16. Lecture 16: Online Linear Bandits [Notes]

17. Lecture 17: Stochastic Multi-armed Bandits [Notes]

18. Lecture 18: Stochastic Multi-armed Bandits [Notes]

19. Lecture 19: Stochastic Multi-armed Bandits, Lower Bounds [Notes]

20. Lecture 20: Contextual Bandits [Notes]

21. Lecture 20: Contextual Bandits: Oracle Efficient Algorithms [Previous Notes] [Notes]

---