Français Anglais
Accueil Annuaire Plan du site
Accueil > Evenements > Séminaires
Séminaire d'équipe(s) Large-scale Heterogeneous DAta and Knowledge
Distributing Frank-Wolfe via Map-Reduce
Stratis Ioannidis

12 October 2017, 10:30 - 12 October 2017, 12:00
Salle/Bat : 455/PCRI-N
Contact :

Activités de recherche : Web data management

Résumé :
Large-scale optimization problems abound in data mining and
machine learning applications, and the computational challenges they pose are often addressed through parallelization. We identify structural properties under which a convex optimization problem can be massively parallelized via map-reduce operations using the Frank-Wolfe (FW) algorithm. The class of problems that can be tackled this way is quite broad and includes experimental design, AdaBoost, and projection
to a convex hull. Implementing FW via map-reduce eases parallelization and deployment via commercial distributed computing frameworks. We demonstrate this by implementing FW over Spark, an engine for parallel data processing, and establish that parallelization through map-reduce yields significant performance improvements: we solve problems with 10 million variables using 350 cores in 44 minutes; the same operation takes 133 hours when executed serially.

Pour en savoir plus :
Séminaires
Forum dev-LRI
Wednesday 05 February 2020 - 14:00
Salle : 455 - PCRI-N
Erik Bray .............................................

Quantum at LRI
Quantum computing
Tuesday 04 February 2020 - 09:00
Salle : 465 - PCRI-N
.............................................

Progressive Data Analysis: a new computation parad
Web data management
Friday 24 January 2020 - 14:00
Salle : 435 - PCRI-N
Jean-Daniel Fekete .............................................

Jeux d’instructions : des extensions SIMD aux exte
Parallel architectures
Tuesday 21 January 2020 - 10:30
Salle : 465 - PCRI-N
Daniel Etiemble .............................................

Forum dev-LRI
Tuesday 14 January 2020 - 14:00
Salle : 445 - PCRI-N
Erik Bray .............................................