On the Non-Asymptotic Concentration of Heteroskedastic Wishart-type Matrix

TL;DR

This paper establishes non-asymptotic spectral norm concentration bounds for heteroskedastic Wishart matrices, providing theoretical guarantees and applications to clustering under heteroskedastic noise.

Contribution

It derives sharp concentration inequalities and minimax bounds for heteroskedastic Wishart matrices, extending results to sub-Gaussian and heavy-tailed distributions, and applies to clustering problems.

Findings

Upper bounds on spectral norm deviations of heteroskedastic Wishart matrices.

Matching minimax lower bounds for the spectral norm.

Application to signal-to-noise ratio thresholds in clustering.

Abstract

This paper focuses on the non-asymptotic concentration of the heteroskedastic Wishart-type matrices. Suppose $Z$ is a $p_1$-by-$p_2$ random matrix and $Z_{ij} \sim N(0,\sigma_{ij}^2)$ independently, we prove the expected spectral norm of Wishart matrix deviations (i.e., $\mathbb{E} \left\|ZZ^\top - \mathbb{E} ZZ^\top\right\|$) is upper bounded by \begin{equation*} \begin{split} (1+\epsilon)\left\{2\sigma_C\sigma_R + \sigma_C^2 + C\sigma_R\sigma_*\sqrt{\log(p_1 \wedge p_2)} + C\sigma_*^2\log(p_1 \wedge p_2)\right\}, \end{split} \end{equation*} where $\sigma_C^2 := \max_j \sum_{i=1}^{p_1}\sigma_{ij}^2$, $\sigma_R^2 := \max_i \sum_{j=1}^{p_2}\sigma_{ij}^2$ and $\sigma_*^2 := \max_{i,j}\sigma_{ij}^2$. A minimax lower bound is developed that matches this upper bound. Then, we derive the concentration inequalities, moments, and tail bounds for the heteroskedastic Wishart-type matrix under more general distributions, such as sub-Gaussian and heavy-tailed distributions. Next, we consider the cases where $Z$ has homoskedastic columns or rows (i.e., $\sigma_{ij} \approx \sigma_i$ or $\sigma_{ij} \approx \sigma_j$) and derive the rate-optimal Wishart-type concentration bounds. Finally, we apply the developed tools to identify the sharp signal-to-noise ratio threshold for consistent clustering in the heteroskedastic clustering problem.