Sharp thresholds for high-dimensional and noisy recovery of sparsity


The problem of consistently estimating the sparsity pattern of a vector β * ∈ R p based on observations contaminated by noise arises in various contexts, including subset selection in regression, structure estimation in graphical models, sparse approximation, and signal denoising. We analyze the behavior of ℓ 1-constrained quadratic programming (QP), also referred to as the Lasso, for recovering the sparsity pattern. Our main result is to establish a sharp relation between the problem dimension p, the number s of non-zero elements in β * , and the number of observations n that are required for reliable recovery. For a broad class of Gaussian ensembles satisfying mutual incoherence conditions, we establish existence and compute explicit values of thresholds θ ℓ and θ u with the following properties: for any ν > 0, if n > 2 (θ u +ν) log(p−s)+s+1, then the Lasso succeeds in recovering the sparsity pattern with probability converging to one for large problems, whereas for n < 2 (θ ℓ − ν) log(p − s) + s + 1, then the probability of successful recovery converges to zero. For the special case of the uniform Gaussian ensemble, we show that θ ℓ = θ u = 1, so that the threshold is sharp and exactly determined.

Extracted Key Phrases

2 Figures and Tables

Showing 1-10 of 36 references

Model selection with the lasso

  • P Zhao, B Yu
  • 2006
Highly Influential
5 Excerpts
Showing 1-10 of 186 extracted citations


Citations per Year

278 Citations

Semantic Scholar estimates that this publication has received between 225 and 349 citations based on the available data.

See our FAQ for additional information.