Anisotropic spectral cut-off estimation under multiplicative measurement errors

TL;DR

This paper introduces a data-driven spectral cut-off method for non-parametric density estimation on R+^d with multiplicative errors, leveraging Mellin transforms and anisotropic regularization to achieve minimax optimality.

Contribution

It develops a novel fully-data driven spectral cut-off estimator using Mellin transforms and anisotropic regularization, with proven minimax optimality in Mellin-Sobolev spaces.

Findings

The estimator achieves minimax optimal rates.

The method effectively handles multiplicative measurement errors.

Anisotropic cut-off selection improves bias-variance trade-off.

Abstract

We study the non-parametric estimation of an unknown density f with support on R+^d based on an i.i.d. sample with multiplicative measurement errors. The proposed fully-data driven procedure is based on the estimation of the Mellin transform of the density f and a regularisation of the inverse of the Mellin transform by a spectral cut-off. The upcoming bias-variance trade-off is dealt with by a data-driven anisotropic choice of the cut-off parameter. In order to discuss the bias term, we consider the Mellin-Sobolev spaces which characterize the regularity of the unknown density f through the decay of its Mellin transform. Additionally, we show minimax-optimality over Mellin-Sobolev spaces of the spectral cut-off density estimator.