Chargement...
 

Historique: Seminar17022015

Aperçu de cette version: 2

February 17th

14:30 , R2014 Digiteo Shannon (660) (see location):


Aurélien Bellet



Title :

The Frank-Wolfe Algorithm: Recent Results and Applications to High-Dimensional Similarity Learning and Distributed Optimization

Abstract :

The topic of this talk is the Frank-Wolfe (FW) algorithm, a greedy procedure for minimizing a convex and differentiable function over a compact convex set. FW finds its roots in the 1950's but has recently regained a lot of interest in machine learning and related communities. In the first part of the talk, I will introduce the FW algorithm and review some recent results that motivate its appeal in the context of large-scale learning problems. In the second part, I will describe two applications of FW in my own work: (i) learning a similarity/distance function for sparse high-dimensional data, and (ii) learning sparse combinations of elements that are distributed over a network.


Contact: cyril.furtlehner à inria.fr

Historique

Avancé
Information Version
mer. 18 de Feb, 2015 10h11 furtlehn from 129.175.15.11 5
Afficher
mer. 18 de Feb, 2015 10h11 furtlehn from 129.175.15.11 4
Afficher
ven. 30 de Jan, 2015 11h19 furtlehn from 129.175.15.11 3
Afficher
ven. 30 de Jan, 2015 11h19 furtlehn from 129.175.15.11 2
Afficher
ven. 30 de Jan, 2015 11h18 furtlehn from 129.175.15.11 1
Afficher