The ability to recover a low-rank matrix from a subset of its entries is the leitmotif of recent advances for localization of wireless sensors, unveiling traffic anomalies in backbone networks, and preference modeling for recommender systems. This paper develops a distributed algorithm for low-rank matrix completion over networks. While nuclear-norm minimization has well-documented merits when centralized processing is viable, the singular-value sum is non-separable and this challenges its minimization in a distributed fashion. To overcome this limitation, an alternative characterization of the nuclear norm is adopted which leads to a separable, yet non-convex cost that is minimized via the alternating-direction method of multipliers. The novel distributed iterations entail reduced-complexity per node tasks, and affordable message passing between single-hop neighbors. Interestingly, upon convergence the distributed (non-convex) estimator provably attains the global optimum of its centralized counterpart, regardless of initialization. Simulations corroborate the convergence of the novel distributed matrix completion algorithm, and its centralized performance guarantees.
[1]
Morteza Mardani,et al.
Decentralized Sparsity-Regularized Rank Minimization: Algorithms and Applications
,
2012,
IEEE Transactions on Signal Processing.
[2]
Emmanuel J. Candès,et al.
Matrix Completion With Noise
,
2009,
Proceedings of the IEEE.
[3]
Gonzalo Mateos,et al.
Distributed Sparse Linear Regression
,
2010,
IEEE Transactions on Signal Processing.
[4]
John N. Tsitsiklis,et al.
Parallel and distributed computation
,
1989
.
[5]
Emmanuel J. Candès,et al.
Exact Matrix Completion via Convex Optimization
,
2008,
Found. Comput. Math..
[6]
Morteza Mardani,et al.
Decentralized Sparsity-Regularized Rank Minimization: Algorithms and Applications
,
2012,
IEEE Transactions on Signal Processing.
[7]
Christopher Ré,et al.
Parallel stochastic gradient algorithms for large-scale matrix completion
,
2013,
Mathematical Programming Computation.
[8]
Pablo A. Parrilo,et al.
Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
,
2007,
SIAM Rev..