Poster
On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems
Yingjie Bi · Javad Lavaei
Keywords: [ Algorithms, Optimization and Computation Methods ] [ Nonconvex Optimization ]
The restricted isometry property (RIP) is a well-known condition that guarantees the absence of spurious local minima in low-rank matrix recovery problems with linear measurements. In this paper, we introduce a novel property named bound difference property (BDP) to study low-rank matrix recovery problems with nonlinear measurements. Using RIP and BDP jointly, we propose a new criterion to certify the nonexistence of spurious local minima in the rank-1 case, and prove that it leads to a much stronger theoretical guarantee than the existing bounds on RIP.