On Sampling Complexity of the Semidefinite Affine Rank Feasibility Problem

In this paper, we study the semidefinite affine rank feasibility problem, which consists in finding a positive semidefinite matrix of a given rank from its linear measurements. We consider the semidefinite programming relaxations of the problem with different objective functions and study their properties. In particular, we propose an analytical bound on the number of relaxations that are sufficient to solve in order to obtain a solution of a generic instance of the semidefinite affine rank feasibility problem or prove that there is no solution. This is followed by a heuristic algorithm based on semidefinite relaxation and an experimental proof of its performance on a large sample of synthetic data.

[1]  Javad Lavaei,et al.  Inverse function theorem for polynomial equations using semidefinite programming , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[2]  Javad Lavaei,et al.  Convexification of Power Flow Equations in the Presence of Noisy Measurements , 2019, IEEE Transactions on Automatic Control.

[3]  A. Tsybakov,et al.  Robust matrix completion , 2014, Probability Theory and Related Fields.

[4]  M. Laurent,et al.  Complexity of the positive semidefinite matrix completion problem with a rank constraint , 2012, 1203.6602.

[5]  Javad Lavaei,et al.  How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery? , 2018, NeurIPS.

[6]  Lijun Zhang,et al.  Efficient Stochastic Optimization for Low-Rank Distance Metric Learning , 2017, AAAI.

[7]  Tengyu Ma,et al.  Matrix Completion has No Spurious Local Minimum , 2016, NIPS.

[8]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[9]  Javad Lavaei,et al.  Finding Low-rank Solutions of Sparse Linear Matrix Inequalities using Convex Optimization , 2017, SIAM J. Optim..

[10]  Anru Zhang,et al.  Compressed Sensing and Affine Rank Minimization Under Restricted Isometry , 2013, IEEE Transactions on Signal Processing.

[11]  Haiyang Li,et al.  Exact recovery low-rank matrix via transformed affine matrix rank minimization , 2016, Neurocomputing.

[12]  T. Chan,et al.  Guarantees of riemannian optimization for low rank matrix completion , 2016, Inverse Problems & Imaging.

[13]  Nathan Srebro,et al.  Global Optimality of Local Search for Low Rank Matrix Recovery , 2016, NIPS.

[14]  Javad Lavaei,et al.  Conic Optimization for Robust Quadratic Regression: Deterministic Bounds and Statistical Analysis , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[15]  Yonina C. Eldar,et al.  Phase Retrieval via Matrix Completion , 2011, SIAM Rev..

[16]  Sergiy A. Vorobyov,et al.  An Algebraic Approach to a Class of Rank-Constrained Semi-Definite Programs With Applications , 2016, ArXiv.

[17]  Hongbin Zha,et al.  A Unified Convex Surrogate for the Schatten-p Norm , 2016, AAAI.

[18]  Jakub Marecek,et al.  Pursuit of Low-Rank Models of Time-Varying Matrices Robust to Sparse and Measurement Noise , 2018, AAAI.

[19]  David P. Wipf,et al.  Pushing the Limits of Affine Rank Minimization by Adapting Probabilistic PCA , 2015, ICML.

[20]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[21]  Javad Lavaei,et al.  A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization , 2018, NeurIPS.

[22]  Maryam Fazel,et al.  Iterative reweighted algorithms for matrix rank minimization , 2012, J. Mach. Learn. Res..

[23]  Pablo A. Parrilo,et al.  Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..

[24]  Inderjit S. Dhillon,et al.  Guaranteed Rank Minimization via Singular Value Projection , 2009, NIPS.

[25]  Weiyu Xu,et al.  Necessary and sufficient conditions for success of the nuclear norm heuristic for rank minimization , 2008, 2008 47th IEEE Conference on Decision and Control.

[26]  Balas K. Natarajan,et al.  Sparse Approximate Solutions to Linear Systems , 1995, SIAM J. Comput..

[27]  Kazuo Murota,et al.  Exploiting Sparsity in Semidefinite Programming via Matrix Completion I: General Framework , 2000, SIAM J. Optim..

[28]  Yi Zheng,et al.  No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis , 2017, ICML.

[29]  Holger Rauhut,et al.  Low rank matrix recovery from rank one measurements , 2014, ArXiv.

[30]  A. Pajor.  Metric Entropy of the Grassmann Manifold , 1998 .

[31]  Yu Zhang,et al.  Conic Relaxations for Power System State Estimation With Line Measurements , 2017, IEEE Transactions on Control of Network Systems.

[32]  Javad Lavaei,et al.  Characterization of rank-constrained feasibility problems via a finite number of convex programs , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[33]  Martin S. Andersen,et al.  Reduced-Complexity Semidefinite Relaxations of Optimal Power Flow Problems , 2013, IEEE Transactions on Power Systems.

[34]  J. Christopher Beck,et al.  Problem Difficulty and the Phase Transition in Heuristic Search , 2017, AAAI.

[35]  Javad Lavaei,et al.  Convexification of Power Flow Equations for Power Systems in Presence of Noisy Measurements , 2016 .