Lectures :

  1. Lecture 1 : Introduction, course details, what is learning theory, learning frameworks [slides]
    Reference : [1] (ch 1 and 3)

  2. Lecture 2 : Learning frameworks, simple examples in binary classification (finite class realizable, bit prediction) [pdf]

  3. Lecture 3 : Minimax Rates, statistical learning and uniform convergence [pdf]

  4. Lecture 4 : Statistical learning, uniform convergence, finite class and MDL principle [pdf]

  5. Lecture 5 : Symmetrization and infinite classes [pdf]

  6. Lecture 6 : Effective size, Growth function and VC dimension [pdf]

  7. Lecture 7 : VC dimension, Massart Lemma, Rademacher Complexity [pdf]

  8. Lecture 8 : Rademacher Complexity [pdf]

  9. Lecture 9 : Covering numbers, Pollard Bound [pdf]

  10. Lecture 10 : Dudley Integral Bound [pdf]

  11. Lecture 11 : Wrapping up Statistical Learning [pdf]

  12. Lecture 12 : Online Learning: Bit Prediction [pdf]

  13. Lecture 13 : Online Learning: Bit Prediction, Dice Prediction, ... [pdf]

  14. Lecture 14 : Online Learning: Bit/Dice Prediction, Experts ... [pdf]

  15. Lecture 15 : Online Convex Optimization [pdf]

  16. Lecture 17 : Online Convex Optimization [pdf]

  17. Lecture 19 : Online Convex Optimization [pdf]

  18. Lecture 20 : General Online Learning and Relaxations [pdf]

  19. Lecture 21 : General Online Learning and Relaxations [pdf]

  20. Lecture 22 : General Online Learning and Relaxations [pdf]

  21. Lecture 23 : General Online Learning and Relaxations [pdf]

  22. Lecture 24 : Randomized Algoeithms Via Relaxations [pdf]