Lectures :

- Lecture 1: Setting Up the Learning Problem [Slides] [lecnotes]

- Lecture 2: Statistical Learning Framework [lecnotes]

- Lecture 3: Statistical Learning, Empirical Risk Minimization and Uniform Convergence [lecnotes]

- Lecture 4: Empirical Risk Minimization, Uniform Convergence and Rademacher Complexity [lecnotes]

- Lecture 5: Binary Classification, Rademacher Complexity, Growth Function and VC Dimension [lecnotes]

- Lecture 6: Rademacher Complexity Properties and Examples [lecnotes]

- Lecture 7: Rademacher Complexity Properties and Examples [lecnotes]

- Lecture 8: Algorithmic Stability [lecnotes]

- Lecture 9: Algorithmic Stability [lecnotes]

- Lecture 10: Algorithmic Stability [lecnotes]

- Lecture 11: Online Learning, Exponential Weights Algorithm [lecnotes]

- Lecture 12: Online Linear and Online Convex Optimization [lecnotes]

- Lecture 13: Boosting [lecnotes]

- Lecture 14: Stochastic Multiarmed Bandit [lecnotes]

- Lecture 15: Stochastic Multiarmed Bandit [lecnotes]

- Lecture 16: Stochastic Multiarmed Bandit [lecnotes]

- Lecture 17: Computational Learning Theory [lecnotes]

- Lecture 18: Computational Learning Theory [lecnotes]

- Lecture 19: Computational Learning Theory: Representation Free [lecnotes]

- Lecture 20: Computational Learning Theory: Representation Free [lecnotes]

- Lecture 21: Differential Privacy [lecnotes] [slides]

- Lecture 22: Differential Privacy [lecnotes]

- Lecture 23: Fairness in Machine Learning [slides]