Improved Rates of Bootstrap Approximation for the Operator Norm: A Coordinate-Free Approach
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916103580549120 |
|---|---|
| author | Lopes, Miles E. |
| author_facet | Lopes, Miles E. |
| contents | Let $\hatΣ=\frac{1}{n}\sum_{i=1}^n X_i\otimes X_i$ denote the sample covariance operator of centered i.i.d.~observations $X_1,\dots,X_n$ in a real separable Hilbert space, and let $Σ=\mathbb{E}(X_1\otimes X_1)$. The focus of this paper is to understand how well the bootstrap can approximate the distribution of the operator norm error $\sqrt n\|\hatΣ-Σ\|_{\text{op}}$, in settings where the eigenvalues of $Σ$ decay as $λ_j(Σ)\asymp j^{-2β}$ for some fixed parameter $β>1/2$. Our main result shows that the bootstrap can approximate the distribution of $\sqrt n\|\hatΣ-Σ\|_{\text{op}}$ at a rate of order $n^{-\frac{β-1/2}{2β+4+ε}}$ with respect to the Kolmogorov metric, for any fixed $ε>0$. In particular, this shows that the bootstrap can achieve near $n^{-1/2}$ rates in the regime of large $β$ -- which substantially improves on previous near $n^{-1/6}$ rates in the same regime. In addition to obtaining faster rates, our analysis leverages a fundamentally different perspective based on coordinate-free techniques. Moreover, our result holds in greater generality, and we propose a model that is compatible with both elliptical and Marčenko-Pastur models in high-dimensional Euclidean spaces, which may be of independent interest. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_03050 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Improved Rates of Bootstrap Approximation for the Operator Norm: A Coordinate-Free Approach Lopes, Miles E. Statistics Theory Probability Let $\hatΣ=\frac{1}{n}\sum_{i=1}^n X_i\otimes X_i$ denote the sample covariance operator of centered i.i.d.~observations $X_1,\dots,X_n$ in a real separable Hilbert space, and let $Σ=\mathbb{E}(X_1\otimes X_1)$. The focus of this paper is to understand how well the bootstrap can approximate the distribution of the operator norm error $\sqrt n\|\hatΣ-Σ\|_{\text{op}}$, in settings where the eigenvalues of $Σ$ decay as $λ_j(Σ)\asymp j^{-2β}$ for some fixed parameter $β>1/2$. Our main result shows that the bootstrap can approximate the distribution of $\sqrt n\|\hatΣ-Σ\|_{\text{op}}$ at a rate of order $n^{-\frac{β-1/2}{2β+4+ε}}$ with respect to the Kolmogorov metric, for any fixed $ε>0$. In particular, this shows that the bootstrap can achieve near $n^{-1/2}$ rates in the regime of large $β$ -- which substantially improves on previous near $n^{-1/6}$ rates in the same regime. In addition to obtaining faster rates, our analysis leverages a fundamentally different perspective based on coordinate-free techniques. Moreover, our result holds in greater generality, and we propose a model that is compatible with both elliptical and Marčenko-Pastur models in high-dimensional Euclidean spaces, which may be of independent interest. |
| title | Improved Rates of Bootstrap Approximation for the Operator Norm: A Coordinate-Free Approach |
| topic | Statistics Theory Probability |
| url | https://arxiv.org/abs/2208.03050 |