2017/2018

Instructor: Nicolas VAYATISTeaching assistant: Xavier FONTAINE

<name/-at-/cmla.ens-cachan.fr>

**************

Room: Condorcet

Date | Time | Instructor | Session | Topics | Files/Readings |

Tuesday October 3 | 11:00-13:00 | N. Vayatis | Lecture #1 | Chapter 1 - Modeling aspects classification data and classification problem |
Slides |

Tuesday October 10 | 08:45-10:45 | N. Vayatis | Lecture #2 | Chapter 1 - Modeling aspects Other problems: convex risk minimization, preference learning, scoring |
Slides |

Tuesday October 17 |
08:00-10:00 | X. Fontaine | Exercise session #1 | Optimal elements and excess risk bounds | Sheet |

Tuesday October 24 |
08:45-10:45 | N. Vayatis | Lecture #3 | Chapter 2 - Mathematical tools Probabilistic inequalities, complexity measures |
Slides |

Tuesday October 31 | 08:45-10:45 | X. Fontaine | Exercise session #2 | Inequalities, Rademacher complexity, VC dimension | Sheet (temporary) |

Tuesday November 7 |
08:45-10:45 | Partial exam - MandatoryNo documents allowed |
|||

Tuesday November 14 |
08:45-10:45 | N. Vayatis | Lecture #4 | Chapter 3 - Consistency of Machine Learning methods SVM and Boosting |
Slides |

Tuesday November 21 |
08:45-10:45 | N. Vayatis | Lecture #5 | Chapter 3 - Consistency of Machine Learning methods Neural networks, bagging, random forests |
Slides |

Tuesday November 28 | 08:45-10:45 | X. Fontaine | Exercise session #3 | Consistency and convergence bounds | Sheet |

Tuesday December 5 |
08:45-10:45 | N. Vayatis | Lecture #6 | Chapter 4 - Advanced topics Multiclass classification, ranking, ... |
Slides |

Tuesday December 12 | 08:45-10:45 | X. Fontaine | Exercise session #4 | Wrap-up | Sheet |

Tuesday December 19 |
08:45-10:45 | Final examDocuments allowed |

Office hours: Tuesdays 1pm/2pm - Laplace 126

**************

Partial exam on November 7 (am) - MANDATORY

Final exam on December 19 (am) - OPTION 1

Project presentations on January 9 (am) - OPTION 2

Grading:

- if OPTION 1 : grade = max(final ; (partial+final)/2)

- if OPTION 2 : grade = (partial+project)/2

**************

Chapter 2 - Tools: Concentration inequalities and complexity measures

Chapter 3 - Theory: Consistency and error bounds of learning algorithms

Chapter 4 - Advanced topics: multiclass classification, ranking, link prediction, ...

- S. Boucheron, O. Bousquet, and G. Lugosi. Theory of Classification: a Survey of Recent Advances. ESAIM: Probability and Statistics, 9:323375, 2005.
- L. Devroye, L. Györfi, G. Lugosi, A Probabilistic Theory of
Pattern Recognition, Springer, New York,
*1996.* - G. Lugosi,
*Principles of Nonparametric Learning*Springer, Wien, New York, pp. 1--56, 2002. - M. Mohri, A. Rostamizadeh, A. Talwalkar. Foundations of Machine
Learning, The MIT Press, 2012.