6 ECTS.<\/p>\n
(En anglais.) This course will review the mathematical foundations for Machine Learning, as well as the underlying algorithmic methods and showcases some modern applications of a broad range of optimization techniques.<\/p>\n
Optimization is at the heart of most recent advances in machine learning. This includes of course most basic methods (linear regression, SVM and kernel methods). It is also the key for the recent explosion of deep learning which are state of the art approaches to solve supervised and unsupervised problems in imaging, vision and natural language processing.<\/p>\n
This course will review the mathematical foundations, the underlying algorithmic methods and showcases some modern applications of a broad range of optimization techniques. The course will be composed of both classical lectures and numerical sessions in Python. The first part covers the basic methods of smooth optimization (gradient descent) and convex optimization (optimality condition, constrained optimization, duality). The second part will features more advanced methods (non-smooth optimization, SDP programming,interior points and proximal methods). The last part will cover large scale methods (stochastic gradient descent), automatic differentiation (using modern python framework) and their application to neural network (shallow and deep nets).<\/p>\n
Lectures will not be at Universit\u00e9 Paris-Dauphine, but at ENS, 29 rue d’Ulm, in the 5th district of Paris. More precisely, lectures will be:<\/p>\n
– Vincent Duval (INRIA)
\n– Robert Gower (Telecom Paris)
\n– Gabriel Peyr\u00e9 (CNRS et ENS)
\n– Cl\u00e9ment Royer (Dauphine)
\n– Alessandro Rudi (INRIA)
\n– Irene Waldspurger (CNRS et Dauphine)<\/p>\n
Theory and algorithms:<\/p>\n
Convex Optimization,<\/em> Boyd and Vandenberghe Numerics:<\/p>\n Pyrthon and Jupyter installation: use only Python 3 with Anaconda distribution.<\/em> 6 ECTS. (En anglais.) This course will review the mathematical foundations for Machine Learning, as well as the underlying algorithmic methods and showcases some modern applications of a broad range of optimization techniques. Optimization is at the heart of most recent advances in machine learning. This includes of course most […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":132,"menu_order":1,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-129","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/pages\/129","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/comments?post=129"}],"version-history":[{"count":0,"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/pages\/129\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/pages\/132"}],"wp:attachment":[{"href":"https:\/\/www.masteriasd.eu\/fr\/wp-json\/wp\/v2\/media?parent=129"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\nIntroduction to matrix numerical analysis and optimization,<\/em> Philippe Ciarlet
\nProximal algorithms,<\/em> N. Parikh and S. Boyd
\nIntroduction to Nonlinear Optimization – Theory, Algorithms and Applications<\/em>, Amir Beck<\/p>\n
\nThe Numerical Tours of Signal Processing,<\/em> Gabriel Peyr\u00e9
\nScikitlearn tutorial #1 and Scikitlearn tutorial #2,<\/em> Fabian Pedregosa, Jake VanderPlas
\nReverse-mode automatic differentiation: a tutorial<\/em>
\nConvolutional Neural Networks for Visual Recognition<\/em>
\nChristopher Olah, Blog<\/p>","protected":false},"excerpt":{"rendered":"