تقرير
Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime
العنوان: | Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime |
---|---|
المؤلفون: | Dubova, Sofiia, Lu, Yue M., McKenna, Benjamin, Yau, Horng-Tzer |
سنة النشر: | 2023 |
المجموعة: | Mathematics Statistics |
مصطلحات موضوعية: | Mathematics - Probability, Statistics - Machine Learning, 60B20, 15B52 |
الوصف: | We consider certain large random matrices, called random inner-product kernel matrices, which are essentially given by a nonlinear function $f$ applied entrywise to a sample-covariance matrix, $f(X^TX)$, where $X \in \mathbb{R}^{d \times N}$ is random and normalized in such a way that $f$ typically has order-one arguments. We work in the polynomial regime, where $N \asymp d^\ell$ for some $\ell > 0$, not just the linear regime where $\ell = 1$. Earlier work by various authors showed that, when the columns of $X$ are either uniform on the sphere or standard Gaussian vectors, and when $\ell$ is an integer (the linear regime $\ell = 1$ is particularly well-studied), the bulk eigenvalues of such matrices behave in a simple way: They are asymptotically given by the free convolution of the semicircular and Mar\v{c}enko-Pastur distributions, with relative weights given by expanding $f$ in the Hermite basis. In this paper, we show that this phenomenon is universal, holding as soon as $X$ has i.i.d. entries with all finite moments. In the case of non-integer $\ell$, the Mar\v{c}enko-Pastur term disappears (its weight in the free convolution vanishes), and the spectrum is just semicircular. Comment: 43 pages, no figures |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2310.18280 |
رقم الأكسشن: | edsarx.2310.18280 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |