Low-rank matrix completion using alternating minimization
Prateek Jain,Praneeth Netrapalli,Sujay Sanghavi +2 more
- pp 665-674
Reads0
Chats0
TLDR
This paper presents one of the first theoretical analyses of the performance of alternating minimization for matrix completion, and the related problem of matrix sensing, and shows that alternating minimizations guarantees faster convergence to the true matrix, while allowing a significantly simpler analysis.Abstract:
Alternating minimization represents a widely applicable and empirically successful approach for finding low-rank matrices that best fit the given data. For example, for the problem of low-rank matrix completion, this method is believed to be one of the most accurate and efficient, and formed a major component of the winning entry in the Netflix Challenge [17].In the alternating minimization approach, the low-rank target matrix is written in a bi-linear form, i.e. X = UV†; the algorithm then alternates between finding the best U and the best V. Typically, each alternating step in isolation is convex and tractable. However the overall problem becomes non-convex and is prone to local minima. In fact, there has been almost no theoretical understanding of when this approach yields a good result.In this paper we present one of the first theoretical analyses of the performance of alternating minimization for matrix completion, and the related problem of matrix sensing. For both these problems, celebrated recent results have shown that they become well-posed and tractable once certain (now standard) conditions are imposed on the problem. We show that alternating minimization also succeeds under similar conditions. Moreover, compared to existing results, our paper shows that alternating minimization guarantees faster (in particular, geometric) convergence to the true matrix, while allowing a significantly simpler analysis.read more
Citations
More filters
Journal ArticleDOI
Exact matrix completion via convex optimization
TL;DR: In this paper, a convex programming problem is used to find the matrix with the minimum nuclear norm that is consistent with the observed entries in a low-rank matrix, which is then used to recover all the missing entries from most sufficiently large subsets.
Book
Convex Optimization: Algorithms and Complexity
TL;DR: This monograph presents the main complexity theorems in convex optimization and their corresponding algorithms and provides a gentle introduction to structural optimization with FISTA, saddle-point mirror prox, Nemirovski's alternative to Nesterov's smoothing, and a concise description of interior point methods.
Journal ArticleDOI
Phase Retrieval via Wirtinger Flow: Theory and Algorithms
TL;DR: In this article, a nonconvex formulation of the phase retrieval problem was proposed and a concrete solution algorithm was presented. But the main contribution is that this algorithm is shown to rigorously allow the exact retrieval of phase information from a nearly minimal number of random measurements.
Journal ArticleDOI
Alternating Minimization Algorithms for Hybrid Precoding in Millimeter Wave MIMO Systems
TL;DR: Treating the hybrid precoder design as a matrix factorization problem, effective alternating minimization (AltMin) algorithms will be proposed for two different hybrid precoding structures, i.e., the fully-connected and partially-connected structures, and simulation comparisons between the two hybrid precode structures will provide valuable design insights.
Proceedings Article
Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition
TL;DR: In this article, the authors show that stochastic gradient descent converges to a local minimum in a polynomial number of iterations for orthogonal tensor decomposition.
References
More filters
Journal ArticleDOI
Matrix Factorization Techniques for Recommender Systems
TL;DR: As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levels.
Journal ArticleDOI
Decoding by linear programming
Emmanuel J. Candès,Terence Tao +1 more
TL;DR: F can be recovered exactly by solving a simple convex optimization problem (which one can recast as a linear program) and numerical experiments suggest that this recovery procedure works unreasonably well; f is recovered exactly even in situations where a significant fraction of the output is corrupted.
Journal ArticleDOI
Robust principal component analysis
TL;DR: In this paper, the authors prove that under some suitable assumptions, it is possible to recover both the low-rank and the sparse components exactly by solving a very convenient convex program called Principal Component Pursuit; among all feasible decompositions, simply minimize a weighted combination of the nuclear norm and of the e1 norm.
Posted Content
Decoding by Linear Programming
Emmanuel J. Candès,Terence Tao +1 more
TL;DR: In this paper, it was shown that under suitable conditions on the coding matrix, the input vector can be recovered exactly by solving a simple convex optimization problem (which one can recast as a linear program).