The anisotropic local law for sample covariance matrices under quadratic-form concentration

Source abstract

We study sample covariance matrices $K = \frac{1}{N} \sum_{i=1}^N \x_i \x_i^* \in \R^{n \times n}$ in the proportional regime $n \asymp N$. The columns $\x_1, \ldots, \x_N \in \R^n$ are independent and centered, with common covariance $\E \x_i \x_i^* = Σ$, but may otherwise have strongly and nonlinearly dependent coordinates. Assuming only that quadratic forms of the columns concentrate uniformly at the optimal rate $| \x_i^* A \x_i - \Tr ΣA | \prec \| A \|_F$, together with polynomial norm moments and a standard nondegeneracy condition on $Σ$, we prove the optimal anisotropic local law: on regular spectral domains, uniformly down to spectral scales $η:= \Im z \geq N^{-1 + τ}$, $$\big| \ \big| \prec \sqrt{\frac{\Im \widetilde m_0 (z)}{Nη}} + \frac{1}{Nη}$$ for all deterministic unit vectors $\u,\bv \in \C^n$, where $\widetilde m_0(z)$ is the Stieltjes transform of the deformed Marchenko-Pastur law. This removes the higher-cumulant tensor assumption of Fan, Ma, Paquette, and Wang (2026), thereby answering the question raised in their work. The result applies, among other examples, to every centered log-concave column distribution with bounded, nondegenerate covariance, nonlinear tilts of Gaussian vectors, deep random features, and a high-temperature spherical 4-spin model for which the cumulant assumption is known to fail.