BriefGPT.xyz
Sep, 2016
应用 Burer-Monteiro 方法消除虚假局部最小值的非方阵矩阵感知
Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach
HTML
PDF
Dohyung Park, Anastasios Kyrillidis, Constantine Caramanis, Sujay Sanghavi
TL;DR
本文探讨了基于受限等距性质(RIP)假设的非方阵矩阵感知问题,并关注了非凸形式化的矩阵分解,证明了矩阵分解不会在 RIP 下引入任何虚假的局部最小值。
Abstract
We consider the
non-square matrix sensing
problem, under
restricted isometry property
(RIP) assumptions. We focus on the
non-convex formulation
→