{"id":391,"date":"2017-11-09T13:31:42","date_gmt":"2017-11-09T13:31:42","guid":{"rendered":"http:\/\/people.irisa.fr\/Remi.Gribonval\/?page_id=391"},"modified":"2020-11-20T16:20:46","modified_gmt":"2020-11-20T16:20:46","slug":"hdl","status":"publish","type":"page","link":"https:\/\/perso.ens-lyon.fr\/remi.gribonval\/talks-and-tutorials\/hdl\/","title":{"rendered":"Cours HDL (High Dimensional Statistical Learning) – M2 SIF"},"content":{"rendered":"

High Dimensional Statistical Learning (HDL)<\/h1>\n

Click here for up to date information on this course<\/a><\/h2>\n

Description<\/h2>\n

This module provides a detailed overview of the mathematical foundations of modern statistical learning by describing the theoretical basis and the conceptual tools needed to analyze and justify the algorithms.\u00a0 The emphasis is on problems involving high volumes of high dimensional datasets, and on dimension reduction techniques allowing to tackle them. The course involves detailed proofs of the main results and associated exercices.<\/p>\n

Keywords<\/h2>\n

PAC (probably approximately correct), random projection, PCA (principal component analysis), concentration inequalities, measures of statistical complexity<\/p>\n

Prerequisites<\/h2>\n

The prerequisites for this course include previous coursework in linear algebra, multivariate calculus, basic probability (continuous and discrete) and statistics.
\nPrevious coursework in convex analysis, information theory, and optimization theory would be helpful but is not required. Students are expected to be able to follow a rigorous proof<\/p>\n

Content<\/h2>\n