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. 2307.09190
18
1

Almost sharp covariance and Wishart-type matrix estimation

18 July 2023
Patrick Oliveira Santos
ArXivPDFHTML
Abstract

Let X1,...,Xn∈RdX_1,..., X_n \in \mathbb{R}^dX1​,...,Xn​∈Rd be independent Gaussian random vectors with independent entries and variance profile (bij)i∈[d],j∈[n](b_{ij})_{i \in [d],j \in [n]}(bij​)i∈[d],j∈[n]​. A major question in the study of covariance estimation is to give precise control on the deviation of ∑j∈[n]XjXjT−EXjXjT\sum_{j \in [n]}X_jX_j^T-\mathbb{E} X_jX_j^T∑j∈[n]​Xj​XjT​−EXj​XjT​. We show that under mild conditions, we have \begin{align*} \mathbb{E} \left\|\sum_{j \in [n]}X_jX_j^T-\mathbb{E} X_jX_j^T\right\| \lesssim \max_{i \in [d]}\left(\sum_{j \in [n]}\sum_{l \in [d]}b_{ij}^2b_{lj}^2\right)^{1/2}+\max_{j \in [n]}\sum_{i \in [d]}b_{ij}^2+\text{error}. \end{align*} The error is quantifiable, and we often capture the 444th-moment dependency already presented in the literature for some examples. The proofs are based on the moment method and a careful analysis of the structure of the shapes that matter. We also provide examples showing improvement over the past works and matching lower bounds.

View on arXiv
Comments on this paper