Structured prediction is the problem of learning a prediction mapping between inputs and structured outputs, i.e. outputs that are made of interrelated parts often subject to constraints. Examples include predicting trees, orderings, alignments, etc., and appear in many applications from computer vision, natural language processing and computational biology among others.
This is an advanced machine learning course that will focus on the fundamental principles and related tools for structured prediction. The course will review the state of the art, tie older and newer approaches together, as well as identify open questions. It will consist of a mix of faculty lectures, class discussions and paper presentations by students, as well as a research project.
Prerequisite: I will assume that most of the content of IFT 6269 Probabilistic Graphical Models is known by the students.
Teacher: Simon Lacoste-Julien, Office: 3339 André-Aisenstadt
Winter 2017 semester:
Wednesdays 10h30-12h30 - Z-305 Pav. Claire-McNicoll
Friday 15h00-17h00 - Z-205 Pav. Claire-McNicoll
Project - project report to hand in + poster presentation on April 28th | detailed info
Lecture notes + references (password protected).
energy-based models & surrogate losses
theory of structured prediction: consistency, etc.
the generative learning / discriminative learning continuum
conditional random field (CRF)
latent variable structured SVM, CCCP algorithm
large-scale optimization: Frank-Wolfe, variance-reduced SGD, block-coordinate methods
learning to search
RNN & friends
combinatorial algorithms: min-cost network flow, submodular optimization, dynamic programs
Last modified: 2017-03-23