Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
Nov 11, 2015 · Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture. Authors:Ju Sun, Qing Qu, John Wright.
Abstract—We consider the problem of recovering a complete. (i.e., square and invertible) matrix A0, from Y ∈ Rn× p with.
Nov 23, 2016 · In this paper, we provide a geometric characterization of the objective landscape. In particular, we show that the problem is highly structured ...
Apr 26, 2015 · This recovery problem is central to the theoretical understanding of dictionary learning, which seeks a sparse representation for a collection ...
Missing: Picture. | Show results with:Picture.
A geometric characterization of the objective landscape is provided, showing that the problem is highly structured with high probability: 1) there are no ...
Dec 2, 2015 · This particular geometric structure allows us to design a Riemannian trust region algorithm over the sphere that provably converges to one local ...
This work gives the first efficient algorithm that provably recovers A0 when X0 has O (n) nonzeros per column, under suitable probability model for X0, ...
Missing: Picture. | Show results with:Picture.
Apr 26, 2015 · The reason that our algorithm is successful derives from the geometry depicted in Figure 2 and formalized in Theorem 2.1. Basically, the sphere ...
Apr 26, 2015 · ... geometric structure allows us to design a Riemannian trust region algorithm over the sphere that provably converges to one local minimizer ...