On the Linear Convergence of the Proximal Gradient Method for Trace Norm Regularization

58 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Guaranteed Matrix Completion via Non-Convex Factorization (2014, background): “Index Terms —Matrix completion, matrix factorization, nonconvex optimization, alternating minimization, SGD, perturbation analysis.”
Decimeter-Level Localization with a Single WiFi Access Point (2016, methodology): “Our approach to optimize for it borrows from proximal gradient methods, a special class of optimization algorithms that have provable convergence guarantees [24].”
A unified approach to error bounds for structured convex optimization problems (2015, methodology): “Speciﬁcally, contrary to what was claimed in [13, Supplementary Material, Section C], the matrices U k and V k that satisfy displayed equations (37) and (38) need not satisfy displayed equation (35).”