ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2010.11921
21
12

Multivariate mean estimation with direction-dependent accuracy

22 October 2020
Gabor Lugosi
S. Mendelson
ArXivPDFHTML
Abstract

We consider the problem of estimating the mean of a random vector based on NNN independent, identically distributed observations. We prove the existence of an estimator that has a near-optimal error in all directions in which the variance of the one dimensional marginal of the random vector is not too small: with probability 1−δ1-\delta1−δ, the procedure returns \whμN\wh{\mu}_N\whμN​ which satisfies that for every direction u∈Sd−1u \in S^{d-1}u∈Sd−1, \[ \inr{\wh{\mu}_N - \mu, u}\le \frac{C}{\sqrt{N}} \left( \sigma(u)\sqrt{\log(1/\delta)} + \left(\E\|X-\EXP X\|_2^2\right)^{1/2} \right)~, \] where σ2(u)=\var(\inrX,u)\sigma^2(u) = \var(\inr{X,u})σ2(u)=\var(\inrX,u) and CCC is a constant. To achieve this, we require only slightly more than the existence of the covariance matrix, in the form of a certain moment-equivalence assumption. The proof relies on novel bounds for the ratio of empirical and true probabilities that hold uniformly over certain classes of random variables.

View on arXiv
Comments on this paper