Reference : Large Margin Classification with the Progressive Hedging Algorithm

	Document type :	Scientific congresses and symposiums : Unpublished conference
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/80247

Title :	Large Margin Classification with the Progressive Hedging Algorithm
Language :	English
Author, co-author :	Defourny, Boris [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore) >]
	Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Publication date :	Dec-2009
On invitation :	No
Audience :	International
Event name :	Second NIPS Workshop on Optimization for Machine Learning
Event date :	December 12, 2009
Event organizer :	Sebastian Nowozin; Suvrit Sra; SVN Vishwanathan; Stephen Wright
Event place (city) :	Whistler
Event country :	Canada
Keywords :	[en] SVM ; parallel algorithms ; stochastic programming
Abstract :	[en] Several learning algorithms in classification and structured prediction are formulated as large scale optimization problems. We show that a generic iterative reformulation and resolving strategy based on the progressive hedging algorithm from stochastic programming results in a highly parallel algorithm when applied to the large margin classification problem with nonlinear kernels. We also underline promising aspects of the available analysis of progressive hedging strategies.
Research units :	Systems and Modeling Research Unit
Funders :	DYSCO (Dynamical Systems, Control, and Optimization); PASCAL2 Network of Excellence
Target :	Researchers ; Professionals ; Students
Permalink :	http://hdl.handle.net/2268/80247

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access OPT2009-Defourny.pdf Author postprint 110.33 kB View/Open

All documents in ORBi are protected by a user license.

 

© ULg Library Network |  Feedback |  ORBi legal notices

Dspace v1.5