Matrix Completion under Low-Rank Missing Mechanism

  title={Matrix Completion under Low-Rank Missing Mechanism},
  author={Xiaojun Mao and Raymond K. W. Wong and S. Chen},
  • Xiaojun Mao, Raymond K. W. Wong, S. Chen
  • Published 2018
  • Mathematics, Computer Science
  • ArXiv
  • Matrix completion is a modern missing data problem where both the missing structure and the underlying parameter are high dimensional. Although missing structure is a key component to any missing data problems, existing matrix completion methods often assume a simple uniform missing mechanism. In this work, we study matrix completion from corrupted data under a novel low-rank missing mechanism. The probability matrix of observation is estimated via a high dimensional low-rank matrix estimation… CONTINUE READING
    1 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper


    Matrix Completion With Covariate Information
    • 8
    Estimation of high-dimensional low-rank matrices
    • 294
    • PDF
    Spectral Regularization Algorithms for Learning Large Incomplete Matrices
    • 854
    • PDF
    Matrix completion via max-norm constrained optimization
    • 71
    • PDF
    Nuclear norm penalization and optimal rates for noisy low rank matrix completion
    • 489
    • Highly Influential
    • PDF
    Noisy low-rank matrix completion with general sampling distribution
    • 132
    • Highly Influential
    • PDF
    Exact matrix completion via convex optimization
    • 2,175
    • PDF
    Structured Matrix Completion with Applications to Genomic Data Integration
    • 28
    • PDF
    Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
    • 375
    • Highly Influential
    • PDF
    A Simpler Approach to Matrix Completion
    • B. Recht
    • Mathematics, Computer Science
    • J. Mach. Learn. Res.
    • 2011
    • 788
    • PDF