The squared-error of generalized LASSO: A precise analysis

@article{Oymak2013TheSO,
  title={The squared-error of generalized LASSO: A precise analysis},
  author={S. Oymak and Christos Thrampoulidis and B. Hassibi},
  journal={2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton)},
  year={2013},
  pages={1002-1009}
}
  • S. Oymak, Christos Thrampoulidis, B. Hassibi
  • Published 2013
  • Computer Science, Mathematics
  • 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • We consider the problem of estimating an unknown but structured signal x<sub>0</sub> from its noisy linear observations y = Ax<sub>0</sub> + z ∈ ℝ<sup>m</sup>. To the structure of x<sub>0</sub> is associated a structure inducing convex function f(·). We assume that the entries of A are i.i.d. standard normal N(0, 1) and z ~ N(0, σ<sup>2</sup>I<sub>m</sub>). As a measure of performance of an estimate x* of x<sub>0</sub> we consider the “Normalized Square Error” (NSE) ∥x* - x<sub>0</sub>∥<sub>2… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Asymptotically exact error analysis for the generalized equation-LASSO
    16
    Precise error analysis of the LASSO
    22
    Simple error bounds for regularized noisy linear inverse problems
    20
    Estimating structured signals in sparse noise: A precise noise sensitivity analysis
    8
    Universality of the elastic net error
    5
    High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions
    32

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 103 REFERENCES
    The Noise-Sensitivity Phase Transition in Compressed Sensing
    330
    On the Reconstruction of Block-Sparse Signals With an Optimal Number of Measurements
    334
    The LASSO Risk for Gaussian Matrices
    200
    Stable signal recovery from incomplete and inaccurate measurements
    6149
    A framework to characterize performance of LASSO algorithms
    61
    Decoding by linear programming
    6163
    Structured sparsity-inducing norms through submodular functions
    161