L1-regularized least squares for support recovery of high dimensional single index models with Gaussian designs

Matey Neykov, Jun S. Liu, Tianxi Cai

Research output: Contribution to journalArticlepeer-review

33 Scopus citations

Abstract

It is known that for a certain class of single index models (SIMs) Y = f(Xpx1Tβ0, ε), support recovery is impossible when X ∼ script N (0, IIpxp) and a model complexity adjusted sample size is below a critical threshold. Recently, optimal algorithms based on Sliced Inverse Regression (SIR) were suggested. These algorithms work provably under the assumption that the design X comes from an i.i.d. Gaussian distribution. In the present paper we analyze algorithms based on covariance screening and least squares with L1 penalization (i.e. LASSO) and demonstrate that they can also enjoy optimal (up to a scalar) rescaled sample size in terms of support recovery, albeit under slightly different assumptions on f and ε compared to the SIR based algorithms. Furthermore, we show more generally, that LASSO succeeds in recovering the signed support of β0 if X ∼ script N (0, Σ), and the covariance Σ satisfies the irrepresentable condition. Our work extends existing results on the support recovery of LASSO for the linear model, to a more general class of SIMs.

Original languageEnglish (US)
JournalJournal of Machine Learning Research
Volume17
StatePublished - May 1 2016

Keywords

  • High-dimensional statistics
  • LASSO
  • Single index models
  • Sparsity
  • Support recovery

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'L1-regularized least squares for support recovery of high dimensional single index models with Gaussian designs'. Together they form a unique fingerprint.

Cite this