Introduction to Probabilistic Graphical Models

Guillaume Obozinski - Francis Bach
Ecole des Ponts, ParisTech - INRIA/ENS

Master recherche specialite "Mathématiques Appliquees",
Parcours M2 Mathématiques, Vision et Apprentissage (ENS Cachan), 1er semestre, 2017/2018

IMPORTANT: [ [ [ Please fill this form to be registered in the Moodle for the class.] ] ]

This year, the class will be taught in English. Homeworks and project may be submitted in English or in French.

Classes will take place on Wednesdays from 9am to 12pm at ENS Cachan, in Amphi Curie.

Dates of classes

Below is the tentative schedule, with scribe notes from last year that might be updated for some lectures.

Link to the statistical review of the master, taking place on September 27th and 28th. The material of the review is a prerequisite for this class. Solutions are now available online.

Date	Lecturer	Topics	Polycopié chapters	Scribe notes
October 4th	Francis Bach	Introduction Maximum likelihood Linear regression Logistic regression Generative classification (Fisher discriminant)	5 Slides (intro) Slides ML 6, 7 Slides Regression	Huu Dien Khue Le, Robin Benesse lecture1.pdf lecture1.zip Aymeric Reshef, Claire Vernade lecture2.pdf lecture2.zip
October 11th	Francis Bach	K-means EM Gaussian mixtures	10, 11 Slides EM	Marie d'Autume, Jean-Baptiste Alayrac lecture3.pdf lecture3.zip
October 18th	Guillaume Obozinski	Graph theory Directed graphical models Undirected graphical models	2	Jaime Roquero, JieYing Wu lecture4.pdf lecture4.zip
October 25th	Guillaume Obozinski	Exponential families Information theory	8, 19	Thomas Belhalfaoui, Lénaic Chizat lecture5.pdf lecture5.zip
November 8th	Guillaume Obozinski	Gaussian variables Factor analysis	13, 14	Lucas Plaetevoet, Ismael Belghiti lecture6.pdf lecture6.zip
November 15th Amphi Cauchy Bat. Carnot Ecole des Ponts (info accès)	Francis Bach	Sum-product algorithm HMM	4, 12	Pauline Luc, Mathieu Andreux lecture7.pdf lecture7.tex
November 22nd	Francis Bach	Approximate inference I Sampling and MCMC methods	21	Khalife Sammy, Maryan Morel lecture8.pdf lecture8.zip
November 29th	Guillaume Obozinsi	Approximate inference II: Variational inference	21	Basile Clément, Nathan de Lara lecture9.pdf lecture9.tex
December 20th	Guillaume Obozinski	Bayesian methods Model selection	5.1 and 5.3	Gauthier Gidel, Lilian Besson lecture10.pdf lecture10.zip
January 9th (Amphi Curie)		Final Exam

Homework (tentative schedule)

Homework 1, due date October 18th 2017 (to be submitted on the Moodle): Homework | Data. Now available via the links.

Paper reading

Reading proposals.

The goal of the paper reading is to further the understanding of certain aspects of the course. The following schedule has to be respected.

mid - November	Choose a reading and form a team of three.
Before November 30th	Send an email to the two teachers, in which all members of your team are cc'ed to request our agreement on your choice of team and reading topic.
Before December 20th	Submit a first brief summary of 1 page on your reading.
Before January 16th	Submit your reading report (max 4 pages, on the Moodle)

Description

This course provides a unifying introduction to probabilistic modelling through the framework of graphical models, together with their associated learning and inference algorithms.

References - Class notes

The course will be based on the book in preparation of Michael I. Jordan (UC Berkeley). Printed version of parts of the book (playing the role of the "polycopie") will be available from the Master's administrative assistant one or two weeks after the beginning of classes. We will notify you when they are ready for you to go and pick them up.

Last updated: October 5th, 2017.