Show simple item record

dc.contributor.authorXu, Yangyang
Yin, Wotao
dc.date.accessioned 2018-06-19T17:48:00Z
dc.date.available 2018-06-19T17:48:00Z
dc.date.issued 2012-08
dc.identifier.citation Xu, Yangyang and Yin, Wotao. "A Block Coordinate Descent Method for Multi-Convex Optimization with Applications to Nonnegative Tensor Factorization and Completion." (2012) https://hdl.handle.net/1911/102204.
dc.identifier.urihttps://hdl.handle.net/1911/102204
dc.description.abstract This paper considers block multi-convex optimization, where the feasible set and objective function are generally non-convex but convex in each block of variables. We review some of its interesting examples and propose a generalized block coordinate descent method. Under certain conditions, we show that any limit point satisfies the Nash equilibrium conditions. Furthermore, we establish its global convergence and estimate its asymptotic convergence rate by assuming a property based on the Kurdyka-Lojasiewicz inequality. The proposed algorithms are adapted for factorizing nonnegative matrices and tensors, as well as completing them from their incomplete observations. The algorithms were tested on synthetic data, hyperspectral data, as well as image sets from the CBCL and ORL databases. Compared to the existing state-of-the-art algorithms, the proposed algorithms demonstrate superior performance in both speed and solution quality. The Matlab code is available for download from the authors' homepages.
dc.format.extent 32 pp
dc.title A Block Coordinate Descent Method for Multi-Convex Optimization with Applications to Nonnegative Tensor Factorization and Completion
dc.type Technical report
dc.date.note August 2012
dc.identifier.digital TR12-15
dc.type.dcmi Text


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record