Thresholded Lasso for High Dimensional Variable Selection and Statistical Estimation *

@inproceedings{ZhouThresholdedLF,
  title={Thresholded Lasso for High Dimensional Variable Selection and Statistical Estimation *},
  author={Shuheng Zhou}
}
Given n noisy samples with p dimensions, where n ≪ p, we show that the multi-step thresholding procedure based on the Lasso – we call it the Thresholded Lasso, can accurately estimate a sparse vector β ∈ R p in a linear model Y = Xβ + ǫ, where X n×p is a design matrix normalized to have column ℓ 2 norm √ n, and ǫ ∼ N (0, σ 2 I n). We show that under the restricted eigenvalue (RE) condition (Bickel-Ritov-Tsybakov 09), it is possible to achieve the ℓ 2 loss within a logarithmic factor of the… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 49 references

Restricted eigenvalue conditions on subgaussian random matrices

  • S Zhou
  • Restricted eigenvalue conditions on subgaussian…
  • 2009
Highly Influential
5 Excerpts

Prediction and variable selection with the adaptive lasso

  • S Van De Geer, P Uhlmann, S Zhou
  • Prediction and variable selection with the…
  • 2010
Highly Influential
3 Excerpts

Adaptive Lasso for high dimensional regression and gaussian graphical modeling

  • S Zhou, S Van De Geer, P Uhlmann
  • Adaptive Lasso for high dimensional regression…
  • 2009
Highly Influential
2 Excerpts

Similar Papers

Loading similar papers…