A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent
[article]
2021
arXiv
pre-print
Low-rank matrix estimation is a canonical problem that finds numerous applications in signal processing, machine learning and imaging science. A popular approach in practice is to factorize the matrix into two compact low-rank factors, and then optimize these factors directly via simple iterative methods such as gradient descent and alternating minimization. Despite nonconvexity, recent literatures have shown that these simple heuristics in fact achieve linear convergence when initialized
arXiv:2005.08898v4
fatcat:fi4mfkd45fcvjhdlepfwmyuh2u