A Riemannian approach for structured low-rank matrix learning
international conference on machine learning(2018)
摘要
We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme is it decouples the low-rank and the structural constraints onto separate factors. We formulate the optimization problem on the Riemannian spectrahedron manifold, where the Riemannian framework allows to develop computationally efficient conjugate gradient and trust-region algorithms. Experiments on problems such as Hankel matrix learning, non-negative matrix completion, and robust matrix completion demonstrate the efficacy of our approach.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络