Online identification and tracking of subspaces from highly incomplete information

@article{Balzano2010OnlineIA,
  title={Online identification and tracking of subspaces from highly incomplete information},
  author={Laura Balzano and R. Nowak and B. Recht},
  journal={2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)},
  year={2010},
  pages={704-711}
}
  • Laura Balzano, R. Nowak, B. Recht
  • Published 2010
  • Computer Science, Mathematics
  • 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • This work presents GROUSE (Grassmanian Rank-One Update Subspace Estimation), an efficient online algorithm for tracking subspaces from highly incomplete observations. GROUSE requires only basic linear algebraic manipulations at each iteration, and each subspace update can be performed in linear time in the dimension of the subspace. The algorithm is derived by analyzing incremental gradient descent on the Grassmannian manifold of subspaces. With a slight modification, GROUSE can also be used as… CONTINUE READING
    353 Citations

    Figures and Topics from this paper

    Online Robust Subspace Tracking from Partial Information
    • 97
    • PDF
    Local Convergence of an Algorithm for Subspace Identification from Partial Data
    • 56
    • PDF
    On GROUSE and incremental SVD
    • Laura Balzano, Stephen J. Wright
    • Mathematics, Computer Science
    • 2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)
    • 2013
    • 43
    • PDF
    A robust online subspace estimation and tracking algorithm
    • Hassan Mansour, Xin Jiang
    • Mathematics, Computer Science
    • 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2015
    • 28
    • PDF
    PETRELS: Subspace estimation and tracking from partial observations
    • 33
    • PDF
    Multiscale online tracking of manifolds
    • 8
    • Highly Influenced
    • PDF
    PETRELS: Parallel Subspace Estimation and Tracking by Recursive Least Squares From Partial Observations
    • 120
    • PDF
    Selective erasures for high-dimensional robust subspace tracking
    • 1
    • Highly Influenced
    • PDF
    Intrinsic Grassmann Averages for Online Linear and Robust Subspace Learning
    • 10
    • Highly Influenced
    • PDF
    K-subspaces with missing data
    • 40
    • PDF

    References

    SHOWING 1-10 OF 21 REFERENCES
    High-dimensional Matched Subspace Detection when data are missing
    • 84
    • PDF
    SET: An algorithm for consistent matrix completion
    • Wei Dai, O. Milenkovic
    • Computer Science, Mathematics
    • 2010 IEEE International Conference on Acoustics, Speech and Signal Processing
    • 2010
    • 54
    • Highly Influential
    • PDF
    Fixed point and Bregman iterative methods for matrix rank minimization
    • 891
    • PDF
    A Singular Value Thresholding Algorithm for Matrix Completion
    • 4,111
    • PDF