On the optimality of sliced inverse regression in high dimensions

Qian Lin, Xinran Li, Dongming Huang, Jun S. Liu

Research output: Contribution to journalArticlepeer-review


The central subspace of a pair of random variables (y, x) ∈ Rp+1 is the minimal subspace S such that y x|PSx. In this paper, we consider the minimax rate of estimating the central space under the multiple index model y = f (βτ1 x, βτ2 x,..., βτdx, ε) with at most s active predictors, where x ∼ N(0, Σ) for some class of Σ. We first introduce a large class of models depending on the smallest nonzero eigenvalue λ of var(E[x|y]), over which we show that an aggregated estimator based on the SIR procedure converges at rate d ∧ ((sd + s log(ep/s))/(nλ)). We then show that this rate is optimal in two scenarios, the single index models and the multiple index models with fixed central dimension d and fixed λ. By assuming a technical conjecture, we can show that this rate is also optimal for multiple index models with bounded dimension of the central space.

Original languageEnglish (US)
Pages (from-to)1-20
Number of pages20
JournalAnnals of Statistics
Issue number1
StatePublished - Feb 2021

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'On the optimality of sliced inverse regression in high dimensions'. Together they form a unique fingerprint.

Cite this