• Corpus ID: 251371705

Improved Rates of Bootstrap Approximation for the Operator Norm: A Coordinate-Free Approach

@inproceedings{Lopes2022ImprovedRO,
  title={Improved Rates of Bootstrap Approximation for the Operator Norm: A Coordinate-Free Approach},
  author={Miles E. Lopes},
  year={2022}
}
Let Σ̂ = 1 n∑ni=1Xi⊗Xi denote the sample covariance operator of centered i.i.d. observations X1, . . . ,Xn in a real separable Hilbert space, and let Σ =E(X1⊗X1). The focus of this paper is to understand how well the bootstrap can approximate the distribution of the operator norm error √ n∥Σ̂ − Σ∥op, in settings where the eigenvalues of Σ decay as λj(Σ) ≍ j−2β for some fixed parameter β > 1/2. Our main result shows that the bootstrap can approximate the distribution of √n∥Σ̂ −Σ∥op at a rate of… 

References

SHOWING 1-10 OF 36 REFERENCES

Rates of Bootstrap Approximation for Eigenvalues in High-Dimensional PCA

Under certain assumptions, the bootstrap can achieve the dimension-free rate of r(Σ)/ √ n up to logarithmic factors, and it is shown that applying a transformation to the eigenvalues of Σ̂ before bootstrapping is an important consideration in high-dimensional settings.

A Sharp Lower-tail Bound for Gaussian Maxima with Application to Bootstrap Methods in High Dimensions

The aim of this paper is to develop a bound on the maxima of Gaussian processes, while also allowing for many types of dependence, and makes use of recent refinements of Bourgain and Tzafriri’s “restricted invertibility principle”.

Regularized estimation of large covariance matrices

If the population covariance is embeddable in that model and well-conditioned then the banded approximations produce consistent estimates of the eigenvalues and associated eigenvectors of the covariance matrix.

Bootstrapping the Operator Norm in High Dimensions: Error Estimation for Covariance Matrices and Sketching

The main result shows that the bootstrap can approximate the distribution of T_n at the dimension-free rate of $n^{-\frac{\beta-1/2}{6\beta+4}}$, with respect to the Kolmogorov metric.

Optimal Approximate Matrix Product in Terms of Stable Rank

We prove, using the subspace embedding guarantee in a black box way, that one can achieve the spectral norm guarantee for approximate matrix multiplication with a dimensionality-reducing map having

On Gaussian comparison inequality and its application to spectral analysis of large random matrices

It is shown that two long-standing problems in random matrix theory can be solved: simple bootstrap inference on sample eigenvalues when true eigen values are tied and conducting two-sample Roy's covariance test in high dimensions.

Optimal rates of convergence for covariance matrix estimation

Covariance matrix plays a central role in multivariate statistical analysis. Significant advances have been made recently on developing both theory and methodology for estimating large covariance

Comparison and anti-concentration bounds for maxima of Gaussian random vectors

Slepian and Sudakov–Fernique type inequalities, which compare expectations of maxima of Gaussian random vectors under certain restrictions on the covariance matrices, play an important role in