An iterative hard thresholding estimator for low rank matrix recovery with explicit limiting distribution

@inproceedings{Carpentier2015AnIH,
  title={An iterative hard thresholding estimator for low rank matrix recovery with explicit limiting distribution},
  author={Alexandra Carpentier and Arlene K. H. Kim},
  year={2015}
}
  • Alexandra Carpentier, Arlene K. H. Kim
  • Published 2015
  • Mathematics
  • We consider the problem of low rank matrix recovery in a stochastically noisy high dimensional setting. We propose a new estimator for the low rank matrix, based on the iterative hard thresholding method, and that is computationally efficient and simple. We prove that our estimator is efficient both in terms of the Frobenius risk, and in terms of the entry-wise risk uniformly over any change of orthonormal basis. This result allows us, in the case where the design is Gaussian, to provide the… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    1
    Twitter Mention

    Figures from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-7 OF 7 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 27 REFERENCES

    Confidence intervals and hypothesis testing for high-dimensional regression

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Universal low-rank matrix recovery from Pauli measurements

    • Yi-Kai Liu
    • Computer Science, Physics, Mathematics
    • NIPS
    • 2011
    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    The Power of Convex Relaxation

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Iterative Hard Thresholding for Compressed Sensing

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Normalized Iterative Hard Thresholding for Matrix Completion

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Convergence of Fixed-Point Continuation Algorithms for Matrix Rank Minimization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Recovering Low-Rank Matrices From Few Coefficients in Any Basis

    • David Gross
    • Computer Science, Mathematics, Physics
    • IEEE Transactions on Information Theory
    • 2011
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL