• English
    • français
  • Help
  •  | 
  • Contact
  •  | 
  • About
  •  | 
  • Login
  • HAL portal
  •  | 
  • Pages Pro
  • EN
  •  / 
  • FR
View Item 
  •   LillOA Home
  • Liste des unités
  • Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
  • View Item
  •   LillOA Home
  • Liste des unités
  • Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

A Distributed Frank-Wolfe Framework for ...
  • BibTeX
  • CSV
  • Excel
  • RIS

Document type :
Rapport de recherche
DOI :
10.1007/s10994-018-5713-5
Title :
A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm
Author(s) :
Zheng, Wenjie [Auteur]
Machine Learning and Information Access [MLIA]
Bellet, Aurelien [Auteur] refId
Machine Learning in Information Networks [MAGNET]
Gallinari, Patrick [Auteur]
Machine Learning and Information Access [MLIA]
Institution :
Inria Lille
Publication date :
2017
English keyword(s) :
Frank–Wolfe algorithm
Low-rank learning
Distributed optimization
Trace norm
Multi-task learning
Multinomial logistic regression
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
English abstract : [en]
We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint. We propose DFW-Trace, ...
Show more >
We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint. We propose DFW-Trace, a distributed Frank-Wolfe algorithm which leverages the low-rank structure of its updates to achieve efficiency in time, memory and communication usage. The step at the heart of DFW-Trace is solved approximately using a distributed version of the power method. We provide a theoretical analysis of the convergence of DFW-Trace, showing that we can ensure sublinear convergence in expectation to an optimal solution with few power iterations per epoch. We implement DFW-Trace in the Apache Spark distributed programming framework and validate the usefulness of our approach on synthetic and real data, including the ImageNet dataset with high-dimensional features extracted from a deep neural network.Show less >
Language :
Anglais
ANR Project :
Apprentissage automatique décentralisé et personnalisé sous contraintes
Collections :
  • Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Source :
Harvested from HAL
Files
Thumbnail
  • https://hal.inria.fr/hal-01672066/document
  • Open access
  • Access the document
Thumbnail
  • http://arxiv.org/pdf/1712.07495
  • Open access
  • Access the document
Thumbnail
  • https://hal.inria.fr/hal-01672066/document
  • Open access
  • Access the document
Thumbnail
  • https://hal.inria.fr/hal-01672066/document
  • Open access
  • Access the document
Université de Lille

Mentions légales
Université de Lille © 2017