2009/04/10 by Anatoli B. Juditsky, Oleg V. Lepski, Alexandre B. Tsybakov · 2 citations
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #Machine Learning and Algorithms #Statistical Methods and Inference #math.ST #msc:62G05 #msc:62G20 #stat.TH
paper · pdf · doi:10.1214/08-aos611
published as Annals of Statistics 2009, Vol. 37, No. 3, 1360-1404 · Published in at http://dx.doi.org/10.1214/08-AOS611 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
openalex publication_date 2009/04/10 · arxiv created 2009/06/04 · arxiv updated 2009/12/01 · openalex created_date 2016/06/24 · openalex updated_date 2026/08/01
We study the problem of nonparametric estimation of a multivariate function g: ℝd→ℝ that can be represented as a composition of two unknown smooth functions f: ℝ→ℝ and G: ℝd→ℝ. We suppose that f and G belong to known smoothness classes of functions, with smoothness γ and β, respectively. We obtain the full description of minimax rates of estimation of g in terms of γ and β, and propose rate-optimal estimators for the sup-norm loss. For the construction of such estimators, we first prove an approximation result for composite functions that may have an independent interest, and then a result on adaptation to the local structure. Interestingly, the construction of rate-optimal estimators for composite functions (with given, fixed smoothness) needs adaptation, but not in the traditional sense: it is now adaptation to the local structure. We prove that composition models generate only two types of local structures: the local single-index model and the local model with roughness isolated to a single dimension (i.e., a model containing elements of both additive and single-index structure). We also find the zones of (γ, β) where no local structure is generated, as well as the zones where the composition modeling leads to faster rates, as compared to the classical nonparametric rates that depend only to the overall smoothness of g.