资源分类
》 资源 》论文》A Unified Framework for Structured Low-rank Matrix Learning

A Unified Framework for Structured Low-rank Matrix Learning

2020-03-20 | |  295 |   72 |   0

Abstract

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, an 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 trustregion algorithms. Experiments on problems such as standard/robust/non-negative matrix completion, Hankel matrix learning and multi-task learning demonstrate the efficacy of our approach.

上一篇：QuantTree: Histograms for Change Detection in Multivariate Data Streams

下一篇：K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...