Additive models in high dimensions

Markus Hegland*, Vladimir Pestov

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    2 Citations (Scopus)


    Additive decompositions are established tools in nonparametric statistics and effectively address the curse of dimensionality. For the analysis of the approximation properties of additive decompositions, we introduce a novel framework which includes the number of variables as an ingredient in the definition of the smoothness of the underlying functions. This approach is motivated by the effect of concentration of measure in high dimensional spaces. Using the resulting smoothness conditions, convergence of the additive decompositions is established. Several examples confirm the error rates predicted by our error bounds. Explicit expressions for optimal additive decompositions (in an L2 sense) are given which can be seen as a generalisation of multivariate Taylor polynomials where the monomials are replaced by higher order interactions. The results can be applied to the numerical approximation of functions with hundreds of variables.

    Original languageEnglish
    Pages (from-to)C1205-C1221
    JournalANZIAM Journal
    Issue number5 ELECTRONIC SUPPL.
    Publication statusPublished - 2004


    Dive into the research topics of 'Additive models in high dimensions'. Together they form a unique fingerprint.

    Cite this