Also note that by departmental policy, this course is open only to graduate students (5th year masters are allowed).

Date | Topic | References/Remarks |

PART I: DEPTH | ||

Aug 30 | Logistics and introduction to introduction to ML | SB chapter 2 |

Sep 1 | Perceptrons: Hope, hopelessness, and hope again | SB chapter 9 |

Sep 6 | No class (labor day) | |

Sep 8 | Optimization for ML | Notes |

Sep 10 | Recitation: Optimization | |

Sep 13 | Support vector machines | SB chapter 15 |

Sep 15 | Kernel methods 1 | SB chapter 16 |

Sep 17 | Recitation: Tail bounds | |

Sep 20 | Kernel methods 2 | SB chapter 16 |

Sep 22 | Learning theory 1 | SB Chapters 2 - 5 |

Sep 24 | Recitation: Linear regression, Logistic regression | |

Sept 27 | Recitation: MLE and MAP [Note: This is a recitation on a Monday since Nihar is giving a tutorial at the same time] | |

Sep 29 | Learning theory 3 | SB Chapters 2 - 6 |

Oct 1 | Learning theory 2 [Note: This is a regular lecture on Friday to make up for Monday] | SB Chapters 2 - 6 |

Oct 4 | Learning theory 4 | SB Chapters 6 - 7 |

Oct 6 | Midterm | All material in previous lectures |

Oct 8 | Recitation: Rademacher Complexity | |

PART II: BREADTH | ||

Oct 11 | Neural networks 1: Introduction. Also, midterm discussion. | SB Chapter 20 |

Oct 13 | Neural networks 2: Representation power | |

Oct 18 | Neural networks 3: Training, automatic differentiation, CNNs, ResNet etc. | |

Oct 20 | Theory paper dissection | |

Oct 25 | Model complexity, cross-validation bias-variance tradeoff, interpolation regime, and Neural networks 4 (neural architecture search) | |

Oct 27 | Decision trees, random forests, bagging, bootstrapping | SB Chapter 18 |

Nov 1 | Unsupervised learning: Clustering | SB Chapter 22 |

Nov 3 | Dimensionality reduction | SB Chapter 23 |

Nov 8 | Boosting | SB Chapter 10 |

Nov 10 | Online learning | SB Chapter 21 |

Nov 15 | Semi-supervised learning, Active learning, Multi-armed bandits | Transductive SVM, Active learning, Multi-armed bandits, Ranking via MABs |

Nov 17 | Reinforcement learning | Survey |

Nov 22 | Graphical models, Causality | Graphical models |

Nov 24 | No class (Thanksgiving break) | |

Nov 29 | Fairness, interpretability, explanability | Hiring example, Paper 1, Paper 2 |

Dec 1 | Applied paper dissection |