SIPA

Semidefinite Programming with Applications in Statistical Learning

Coordinatore	CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE    more Spiacenti, non ci sono informazioni su questo coordinatore. Contattare Fabio per maggiori infomrazioni, grazie.
Nazionalità Coordinatore	France [FR]
Totale costo	1˙148˙460 €
EC contributo	1˙148˙460 €
Programma	FP7-IDEAS-ERC Specific programme: "Ideas" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013)
Code Call	ERC-2010-StG_20091028
Funding Scheme	ERC-SG
Anno di inizio	2011
Periodo (anno-mese-giorno)	2011-05-01   -   2016-04-30

 Partecipanti

#	participant	country	role	EC contrib. [€]
1	CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE  Organization address address: Rue Michel -Ange 3 city: PARIS postcode: 75794 contact info Titolo: Ms. Nome: Julie Cognome: Zittel Email: send email Telefono: +33 142349417	FR (PARIS)	hostInstitution	1˙148˙460.00
2	CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE  Organization address address: Rue Michel -Ange 3 city: PARIS postcode: 75794 contact info Titolo: Prof. Nome: Alexandre Werner Geoffroy Gobert Cognome: D'aspremont Lynden Email: send email Telefono: +33 6 32 45 49 86 Fax: +33 6 32 45 49 86	FR (PARIS)	hostInstitution	1˙148˙460.00

Mappa

 Word cloud

Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.

 Obiettivo del progetto (Objective)

'Interior point algorithms and a dramatic growth in computing power have revolutionized optimization in the last two decades. Highly nonlinear problems which were previously thought intractable are now routinely solved at reasonable scales. Semidefinite programs (i.e. linear programs on the cone of positive semidefinite matrices) are a perfect example of this trend: reasonably large, highly nonlinear but convex eigenvalue optimization problems are now solved efficiently by reliable numerical packages. This in turn means that a wide array of new applications for semidefinite programming have been discovered, mimicking the early development of linear programming. To cite only a few examples, semidefinite programs have been used to solve collaborative filtering problems (e.g. make personalized movie recommendations), approximate the solution of combinatorial programs, optimize the mixing rate of Markov chains over networks, infer dependence patterns from multivariate time series or produce optimal kernels in classification problems. These new applications also come with radically different algorithmic requirements. While interior point methods solve relatively small problems with a high precision, most recent applications of semidefinite programming in statistical learning for example form very large-scale problems with comparatively low precision targets, programs for which current algorithms cannot form even a single iteration. This proposal seeks to break this limit on problem size by deriving reliable first-order algorithms for solving large-scale semidefinite programs with a significantly lower cost per iteration, using for example subsampling techniques to considerably reduce the cost of forming gradients. Beyond these algorithmic challenges, the proposed research will focus heavily on applications of convex programming to statistical learning and signal processing theory where optimization and duality results quantify the statistical performance of coding or variable selection algorithms for example. Finally, another central goal of this work will be to produce efficient, customized algorithms for some key problems arising in machine learning and statistics.'