Metraipolis › archive › dc_92d613ec2b1e
Statistical Guarantees for Covariance Estimation with Adversarial Corruption under Constraints — arXiv:2610.10840
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10840
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:28:16.651Z
- SHA-256 of the archived text
fdc3c428750ed530336415ac9caf1a009dfcab9d6a2cb390f3bd69ba8bb748b9- Stable URL of this page
https://metraipolis.com/documento/dc_92d613ec2b1e
How to cite
Statistical Guarantees for Covariance Estimation with Adversarial Corruption under Constraints — arXiv:2610.10840 — arXiv (en), https://arxiv.org/abs/2610.10840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_92d613ec2b1e (Metraipolis archive dc_92d613ec2b1e, sha256 fdc3c428750ed530336415ac9caf1a009dfcab9d6a2cb390f3bd69ba8bb748b9)
BibTeX
@misc{dc92d613ec2b1e,
title = {Statistical Guarantees for Covariance Estimation with Adversarial Corruption under Constraints — arXiv:2610.10840},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10840},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_92d613ec2b1e; sha256 fdc3c428750ed530336415ac9caf1a009dfcab9d6a2cb390f3bd69ba8bb748b9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We obtain a near-minimax rate on covariance estimation of adversarially corrupted Gaussian data in Frobenius norm when the covariance estimation is assumed to lie in a star-shaped set $K \subseteq \mathbb{R}^{n \times n}$. Assuming a known upper bound of $\varepsilon < 1/32$ on the fraction of the $N$ observations of data $X$ are arbitrarily corrupted by an omniscient adversary, we obtain the near-minimax rate (up to constants) of \begin{align*} \left(\varepsilon^2 \vee \delta^{\star2} \right)\wedge d^2 \lesssim \inf_{\hat\Sigma} \sup_{\Sigma \in K} \sup_{\mathrm{C}} \mathbb{E} \| \hat\Sigma(\mathrm{C}(X)) - \Sigma \|_F^2 \lesssim \left(\varepsilon^2\log^2(1/\varepsilon) \vee \delta^{\star2} \right)\wedge d^2 \end{align*} where $d$ is the diameter of the set $K$, $N \gtrsim \sup_{\delta > 0} \log \mathrm{M}^{\operatorname{loc}}(\delta, 2c)$, and \begin{align*} \delta^*=\sup\left\{ \delta\geq 0: \frac{N}{\Upsilon^2} \delta^2\leq \log \mathrm{M}_K^{\operatorname{loc}}(\delta,c) \right\} \end{align*} for an arbitrary large constant $c$ and the local metric entropy of $K$, $\mathrm{M}^{\operatorname{loc}}_K(\delta,c)$. We believe this is the first such general result on structured robust covariance estimation in the Frobenius norm.
Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2610.10840 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:52:46.492Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).