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, Going to Infinite Classes [pdf]

  4. Lecture 4: MDL Principle, Covering Numbers, Symmetrization [pdf]

  5. Lecture 5: Symmetrization, Rademacher Complexity and Massart's Finite Lemma [pdf]

  6. Lecture 6: Massart's Finite Lemma Continued, Binary Classification, Growth Function, VC dimension and VC Lemma [pdf]

  7. Lecture 7: Rademacher Complexity [pdf]

  8. Lecture 8: Rademacher Complexity [pdf]

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

  10. Lecture 10: Wrapping Statistical Learning [pdf]

  11. Lecture 11: Online Games [pdf]

  12. Lecture 12: Online Games continued [pdf]

  13. Lecture 13: Online Convex Optimization [pdf]

  14. Lecture 14: Online Mirror Descent [pdf] [Supplementary Material]

  15. Lecture 15: Online Mirror Descent [pdf] [Supplementary Material]

  16. Lecture 16: Online Mirror Descent, Fater Rates For Curved Losses [pdf]

  17. Lecture 17: Relaxations for General Online Learning [pdf]

  18. Lecture 18: Relaxations for General Online Learning [pdf]

  19. Lecture 19: Online Linear Bandit Problem [pdf]

  20. Lecture 20: Online Linear Bandit Problem [pdf]

  21. Lecture 21: Stability and Learning [pdf]

  22. Lecture 22: Stability and Learning [pdf]

  23. Lecture 23: Stability Based Analysis [pdf]

  24. Lecture 24: Boosting an Online Learning [pdf] Nice illustrative example By Robert Schapire at [link]

  25. Lecture 25: Stochastic Multi-armed Bandit [pdf]

  26. Lecture 26: Stochastic Multi-armed Bandit, Lower Bounds [pdf]

  27. Lecture 27: Contextual Bandit and Semi-Bandits [pdf]

  28. Lecture 28: Last Lecture [pdf]


Email: sridharan at cs dot cornell dot edu