Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

arXiv2301.11808MaRDI QIDQ6424601FDOQ6424601

Authors: Dat Do, Huy Nguyen, Khai Q. Nguyen, Nhat Ho 

Publication date: 27 January 2023

Abstract: We study the maximum likelihood estimation (MLE) in the matrix-variate deviated models where the data are generated from the density function $(1-lambd{a}^{\ast })h_0(x)+lambd{a}^{\ast }f(x|m{u}^{\ast },Sigm{a}^{\ast })$ where $h_0$ is a known function, $lambd{a}^{\ast }in[0,1]$ and $(m{u}^{\ast },Sigm{a}^{\ast })$ are unknown parameters to estimate. The main challenges in deriving the convergence rate of the MLE mainly come from two issues: (1) The interaction between the function $h_0$ and the density function $f$; (2) The deviated proportion $lambd{a}^{\ast }$ can go to the extreme points of $[0,1]$ as the sample size goes to infinity. To address these challenges, we develop the distinguishability condition to capture the linear independent relation between the function $h_0$ and the density function $f$. We then provide comprehensive convergence rates of the MLE via the vanishing rate of $lambd{a}^{\ast }$ to 0 as well as the distinguishability of $h_0$ and $f$.

This page was built for publication: Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6424601)