对抗污染下带约束的协方差估计的统计保证
Statistical Guarantees for Covariance Estimation with Adversarial Corruption under Constraints
浏览论文内容
中文总结 AI 辅助
针对对抗污染的高斯数据,在协方差估计值位于星形集的约束下,该研究得到了 Frobenius 范数下结构化鲁棒协方差估计的首个近极小极大速率的一般性统计保证结果。
中文摘要 AI 辅助
当协方差估计值位于星形集 $K \subseteq \mathbb{R}^{n \times n}$ 中时,我们针对对抗污染的高斯数据的协方差估计,在 Frobenius 范数下得到了近极小极大速率。假设数据 $X$ 的 $N$ 个观测值中,有任意比例的 $\varepsilon < 1/32$ 被全知对手任意污染,我们得到了近极小极大速率(相差常数因子):\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*} 其中 $d$ 是集合 $K$ 的直径,$N \gtrsim \sup_{\delta > 0} \log \mathrm{M}^{\operatorname{loc}}(\delta, 2c)$,且 \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*},$c$ 为任意大的常数,$\mathrm{M}_K^{\operatorname{loc}}(\delta,c)$ 是 $K$ 的局部度量熵。我们认为这是首个关于 Frobenius 范数下结构化鲁棒协方差估计的此类一般性结果。
英文摘要
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 δ^{\star2} \right)\wedge d^2 \lesssim \inf_{\hatΣ} \sup_{Σ\in K} \sup_{\mathrm{C}} \mathbb{E} \| \hatΣ(\mathrm{C}(X)) - Σ\|_F^2 \lesssim \left(\varepsilon^2\log^2(1/\varepsilon) \vee δ^{\star2} \right)\wedge d^2 \end{align*} where $d$ is the diameter of the set $K$, $N \gtrsim \sup_{δ> 0} \log \mathrm{M}^{\operatorname{loc}}(δ, 2c)$, and \begin{align*} δ^*=\sup\left\{ δ\geq 0: \frac{N}{Υ^2} δ^2\leq \log \mathrm{M}_K^{\operatorname{loc}}(δ,c) \right\} \end{align*} for an arbitrary large constant $c$ and the local metric entropy of $K$, $\mathrm{M}^{\operatorname{loc}}_K(δ,c)$. We believe this is the first such general result on structured robust covariance estimation in the Frobenius norm.
发表机构
- Northwestern University(西北大学)
机构由 AI 辅助整理,请以论文原文为准。