Compressible distributions for high-dimensional statistics

R. Gribonval, V. Cevher, M.E. Davies

Research output: Contribution to journalArticlepeer-review


We develop a principled way of identifying probability distributions whose independent and identically distributed (iid) realizations are compressible, i.e., can be well-approximated as sparse. We focus on Gaussian random underdetermined linear regression (GULR) problems, where compressibility is known to ensure the success of estimators exploiting sparse regularization. We prove that many distributions revolving around maximum a posteriori (MAP) interpretation of sparse regularized estimators are in fact incompressible, in the limit of large problem sizes. A highlight is the Laplace distribution and $\ell^{1}$ regularized estimators such as the Lasso and Basis Pursuit denoising. To establish this result, we identify non-trivial undersampling regions in GULR where the simple least squares solution almost surely outperforms an oracle sparse solution, when the data is generated from the Laplace distribution. We provide simple rules of thumb to characterize classes of compressible (respectively incompressible) distributions based on their second and fourth moments. Generalized Gaussians and generalized Pareto distributions serve as running examples for concreteness.
Original languageEnglish
Pages (from-to)5016-5034
JournalIEEE Transactions on Information Theory
Issue number8
Publication statusPublished - Aug 2012


  • Basis pursuit
  • Lasso
  • compressed sensing
  • compressible distribution
  • high-dimensional statistics
  • instance optimality


Dive into the research topics of 'Compressible distributions for high-dimensional statistics'. Together they form a unique fingerprint.

Cite this