Convex Sparse Matrix Factorizations

Simple item page
dc.creatorBach, Francis
dc.creatorMairal, Julien
dc.creatorPonce, Jean
dc.date2008-12-10
dc.date.accessioned2026-07-07T12:11:38Z
dc.date.available2026-07-07T12:11:38Z
dc.descriptionWe present a convex formulation of dictionary learning for sparse signal decomposition. Convexity is obtained by replacing the usual explicit upper bound on the dictionary size by a convex rank-reducing term similar to the trace norm. In particular, our formulation introduces an explicit trade-off between size and sparsity of the decomposition of rectangular matrices. Using a large set of synthetic examples, we compare the estimation abilities of the convex and non-convex approaches, showing that while the convex formulation has a single local minimum, this may lead in some cases to performance which is inferior to the local minima of the non-convex formulation.
dc.identifierhttps://arxiv.org/abs/0812.1869
dc.identifierhttp://arxiv.org/abs/0812.1869
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/210281
dc.subjectMachine Learning
dc.titleConvex Sparse Matrix Factorizations
dc.typetext

Files

Collections

arXiv