A Singular Value Thresholding Algorithm for Matrix Completion

Abstract

This paper introduces a novel algorithm to approximate the matrix with minimum nuclear norm among all matrices obeying a set of convex constraints. This problem may be understood as the convex relaxation of a rank minimization problem, and arises in many important applications as in the task of recovering a large matrix from a small subset of its entries (the famous Netflix problem). Off-the-shelf algorithms such as interior point methods are not directly amenable to large problems of this kind with over a million unknown entries.This paper develops a simple first-order and easy-to-implement algorithm that is extremely efficient at addressing problems in which the optimal solution has low rank. The algorithm is iterative and produces a sequence of matrices {X k , Y k } and at each step, mainly performs a soft-thresholding operation on the singular values of the matrix Y k . There are two remarkable features making this attractive for low-rank matrix completion problems. The first is that the soft-thresholding operation is applied to a sparse matrix; the second is that the rank of the iterates {X k } is empirically nondecreasing. Both these facts allow the algorithm to make use of very minimal storage space and keep the computational cost of each iteration low. On the theoretical side, we provide a convergence analysis showing that the sequence of iterates converges. On the practical side, we provide numerical examples in which 1, 000×1, 000 matrices are recovered in less than a minute on a modest desktop computer. We also demonstrate that our approach is amenable to very large scale problems by recovering matrices of rank about 10 with nearly a billion unknowns from just about 0.4% of their sampled entries. Our methods are connected with the recent literature on linearized Bregman iterations for ℓ 1 minimization, and we develop a framework in which one can understand these algorithms in terms of well-known Lagrange multiplier algorithms.

Mirror Descent for Metric Learning: A Unified Approach

“…The latter is closely related to the trace-norm minimization problem, which was solved by Cai et al, [20]:…”

Multi-task and multi-kernel Gaussian process dynamical systems

“…• SVT [42] and FPC [43]: The methods are dubbed singular value thresholding (SVT) and fixed point completion (FPC). They are both nonBayesian and non-sequential models employing point-wise optimisation for the purpose of matrix completion.…”

A Linear Solution to 1-Dimensional Subspace Fitting under Incomplete Data

“…Minimal and maximal values were about −150 and 150, respectively. We then estimated the subspace using our proposed method and compare it with PowerFactorization [11], an EM-algorithm where subspace and missing data are estimated alternatingly, and an implementation of a nuclear norm minization algorithm (NNM) [5] 2 . Our implementation of the EM-algorithm is similar to [19] yet without considering statistical reliability of trajectories.…”