IFT 6760A - Winter 2019
Matrix and tensor factorization techniques for machine learning

Description

The goal of this course is to present an overview of linear and multilinear algebra techniques for designing/analyzing ML algorithms and models, and to engage students with new research in the area.
- Fundamental notions of linear and multilinear algebra.
- Old and new ML methods leveraging matrix and tensor decomposition: PCA/CCA, collaborative filtering, spectral graph clustering, spectral methods for HMM, K-FAC, spectral normalization, tensor method of moments, NN/MRF compression, tensor regression/completion, etc.
- Open problems.

More infos coming soon...

Class Info

When: Tuesdays 12:30-2:30PM and Thursdays 11:30-1:30PM
Where: (very likely) at Mila (6666 St-Urbain street)
Instructor: Guillaume Rabusseau, Office 3151, André-Aisenstadt
Office hours: Tuesdays after class

Evaluation

Class project + Paper presentation + Scribing + Class participation
(this is subject to change but there will definitely be no closed room exam)

Tentative list of topics (to be updated as we go along)

Schedule

Resources

Linear Algebra

Tensor Decomposition