The number of linear measurements for perfect structured signal recovery depends only on first and second moments of the measurement distribution, reducing analysis to the Gaussian case and yielding 3n measurements for PhaseLift phase retrieval.
New Null Space Results and Recovery Thresholds for Matrix Rank Minimization
2 Pith papers cite this work. Polarity classification is still indexing.
abstract
Nuclear norm minimization (NNM) has recently gained significant attention for its use in rank minimization problems. Similar to compressed sensing, using null space characterizations, recovery thresholds for NNM have been studied in \cite{arxiv,Recht_Xu_Hassibi}. However simulations show that the thresholds are far from optimal, especially in the low rank region. In this paper we apply the recent analysis of Stojnic for compressed sensing \cite{mihailo} to the null space conditions of NNM. The resulting thresholds are significantly better and in particular our weak threshold appears to match with simulation results. Further our curves suggest for any rank growing linearly with matrix size $n$ we need only three times of oversampling (the model complexity) for weak recovery. Similar to \cite{arxiv} we analyze the conditions for weak, sectional and strong thresholds. Additionally a separate analysis is given for special case of positive semidefinite matrices. We conclude by discussing simulation results and future research directions.
fields
math.ST 2representative citing papers
citing papers explorer
-
Universality in Learning from Linear Measurements
The number of linear measurements for perfect structured signal recovery depends only on first and second moments of the measurement distribution, reducing analysis to the Gaussian case and yielding 3n measurements for PhaseLift phase retrieval.
- High-Dimensional Statistics: Reflections on Progress and Open Problems