Zobrazeno 1 - 10
of 256
pro vyhledávání: '"Lafond, Jean"'
Autor:
Lafond, Jean
Dans cette thèse nous nous intéressons aux méthodes de complétion de matrices de faible rang et étudions certains problèmes reliés. Un premier ensemble de résultats visent à étendre les garanties statistiques existantes pour les modèles de
Externí odkaz:
http://www.theses.fr/2016SACLT002/document
We define a second-order neural network stochastic gradient training algorithm whose block-diagonal structure effectively amounts to normalizing the unit activations. Investigating why this algorithm lacks in robustness then reveals two interesting i
Externí odkaz:
http://arxiv.org/abs/1705.09319
Decentralized optimization algorithms have received much attention due to the recent advances in network information processing. However, conventional decentralized algorithms based on projected gradient descent are incapable of handling high dimensi
Externí odkaz:
http://arxiv.org/abs/1612.01216
In this paper, the online variants of the classical Frank-Wolfe algorithm are considered. We consider minimizing the regret with a stochastic cost. The online algorithms only require simple iterative updates and a non-adaptive step size rule, in cont
Externí odkaz:
http://arxiv.org/abs/1510.01171
Autor:
Lafond, Jean
The matrix completion problem consists in reconstructing a matrix from a sample of entries, possibly observed with noise. A popular class of estimator, known as nuclear norm penalized estimators, are based on minimizing the sum of a data fitting term
Externí odkaz:
http://arxiv.org/abs/1502.06919
Autor:
Lafond, Jean-François
Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.
Externí odkaz:
http://hdl.handle.net/1866/7187
Publikováno v:
NIPS, Dec 2014, Montreal, Canada
The task of reconstructing a matrix given a sample of observedentries is known as the matrix completion problem. It arises ina wide range of problems, including recommender systems, collaborativefiltering, dimensionality reduction, image processing,
Externí odkaz:
http://arxiv.org/abs/1412.2632
The task of estimating a matrix given a sample of observed entries is known as the \emph{matrix completion problem}. Most works on matrix completion have focused on recovering an unknown real-valued low-rank matrix from a random sample of its entries
Externí odkaz:
http://arxiv.org/abs/1408.6218