5 papers · 1 filter
Low-rank matrix recovery landscapes beyond RIP with application to rank-one measurements
Andrew D. McRae
We study the problem of low-rank matrix recovery from linear measurements via the global nonconvex landscape of a low-rank factored formulation of the matrix LASSO (nuclear-norm--r…
Spectral Initialization and Certification for Power System Angle Estimation
Iven Guzel, Andrew D. McRae, Richard Y. Zhang
Power System State Estimation (PSSE) is commonly formulated as a nonconvex weighted least-squares (WLS) problem, making global optimality difficult both to attain and to certify. R…
Sharp recovery and landscape guarantees for the nonconvex matrix LASSO
Andrew D. McRae, Richard Y. Zhang
Low-rank matrix recovery can be solved to statistical optimality by convex matrix optimization under the classical assumption of restricted isometry property (RIP). However, for la…
Phase retrieval via overparametrized nonconvex optimization: nonsmooth amplitude loss landscapes
Andrew D. McRae
We study nonconvex optimization for phase retrieval and the more general problem of semidefinite low-rank matrix sensing; in particular, we focus on the global nonconvex landscape…
Phase retrieval and matrix sensing via benign and overparametrized nonconvex optimization
Andrew D. McRae
We study a nonconvex optimization algorithmic approach to phase retrieval and the more general problem of semidefinite low-rank matrix sensing. Specifically, we analyze the nonconv…