Nonparametric estimation by convex programming

From MaRDI portal
Publication:834340

DOI10.1214/08-AOS654zbMATH Open1173.62024arXiv0908.3108WikidataQ57392906 ScholiaQ57392906MaRDI QIDQ834340FDOQ834340

Anatoli Juditsky, Arkadi Nemirovski

Publication date: 19 August 2009

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: The problem we concentrate on is as follows: given (1) a convex compact set X in mathbbRn, an affine mapping xmapstoA(x), a parametric family pmu(cdot) of probability densities and (2) N i.i.d. observations of the random variable omega, distributed with the density pA(x)(cdot) for some (unknown) xinX, estimate the value gTx of a given linear form at x. For several families pmu(cdot) with no additional assumptions on X and A, we develop computationally efficient estimation routines which are minimax optimal, within an absolute constant factor. We then apply these routines to recovering x itself in the Euclidean norm.


Full work available at URL: https://arxiv.org/abs/0908.3108





Cites Work


Cited In (19)






This page was built for publication: Nonparametric estimation by convex programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q834340)