Binary matrix completion with nonconvex regularizers
This work addresses binary matrix recovery for machine learning applications, but it is incremental as it extends nonconvex methods to a specific BMC case.
The paper tackles binary matrix completion with only positive observations by proposing a model with nonconvex regularizers and an accelerated proximal algorithm, achieving a convergence rate of 1/T and demonstrating superiority in experiments on synthetic and real-world datasets.
Many practical problems involve the recovery of a binary matrix from partial information, which makes the binary matrix completion (BMC) technique received increasing attention in machine learning. In particular, we consider a special case of BMC problem, in which only a subset of positive elements can be observed. In recent years, convex regularization based methods are the mainstream approaches for this task. However, the applications of nonconvex surrogates in standard matrix completion have demonstrated better empirical performance. Accordingly, we propose a novel BMC model with nonconvex regularizers and provide the recovery guarantee for the model. Furthermore, for solving the resultant nonconvex optimization problem, we improve the popular proximal algorithm with acceleration strategies. It can be guaranteed that the convergence rate of the algorithm is in the order of ${1/T}$, where $T$ is the number of iterations. Extensive experiments conducted on both synthetic and real-world data sets demonstrate the superiority of the proposed approach over other competing methods.