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, Minimax Rates [pdf]

  3. Lecture 3: No Free Lunch Theorem, ERM, Rates for finite classes [pdf]

  4. Lecture 4: MDL, Uniform rates, Infinite class and Symmetrization [pdf]

  5. Lecture 5: Symmetrization, Rademacher Complexity, Effective Size [pdf]

  6. Lecture 6: Effective size, VC Dimension, Learnability and VC/Sauer/Shelah Lemma [pdf]

  7. Lecture 7: Massart's Finite LEmma, Properties of Rademacher Complexity [pdf]

  8. Lecture 8: Properties of Rademacher Complexity, Contraction Lemma, Examples [pdf]

  9. Lecture 9: Covering Numbers, Pollard Bound and Dudley Chaining [pdf]

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

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

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

  13. Lecture 13: Online Learning: Bit prediction continued + Linear betting game [pdf]

  14. Lecture 14: Online Learning: Bit prediction continued + Linear betting game [pdf]

  15. Lecture 15: Online Convex Optimization: Setting + Online to batch + Gradient Descent [pdf]

  16. Lecture 16: Online Convex Optimization: Setting + Online to batch + Gradient Descent [pdf]

  17. Lecture 17: Online Mirror Descent [pdf]

  18. Lecture 18: Online Mirror Descent and Faster Rates [pdf]

  19. Lecture 19: Betting with Arbitrary Covariates [pdf]

  20. Lecture 20: Betting with Arbitrary Covariates [pdf]

  21. Lecture 21: Sequential Rademacher Complexity [pdf]

  22. Lecture 22: Burkholder Method for Supervised Learning with Convex Losses [pdf]

  23. Matrix Completion using Burkholder Method [pdf]