41 pages, 8 figuresInternational audienceKernel matrices are of central importance to many applied fields. In this manuscript, we focus on spectral properties of kernel matrices in the so-called "flat limit", which occurs when points are close together relative to the scale of the kernel. We establish asymptotic expressions for the determinants of the kernel matrices, which we then leverage to obtain asymptotic expressions for the main terms of the eigenvalues. Analyticity of the eigenprojectors yields expressions for limiting eigenvectors, which are strongly tied to discrete orthogonal polynomials. Both smooth and finitely smooth kernels are covered, with stronger results available in the finite smoothness case
A new form of empirical spectral distribution of a Wigner matrix Wn with weights specified by the ei...
We consider n-by-n matrices whose (i, j)th entry is f(XTi Xj), where X1,..., Xn are i.i.d. standard ...
Scaling level-spacing distribution functions in the ``bulk of the spectrum'' in random matr...
This paper focuses on the spectral distribution of kernel matrices related to radial basis functions...
This paper focuses on spectral distribution of kernel matrices related to radial basis functions. By...
The spectral behavior of kernel matrices built from complex multi-variate data is established in the...
This paper focuses on the spectral distribution of kernel matrices related to radial basis functions...
We study the properties of the eigenvalues of Gram matrices in a non-asymptotic setting. Using local...
Abstract. We study the properties of the eigenvalues of Gram matrices in a non-asymptotic setting. U...
The eigenvalues of the kernel matrix play an important role in a number of kernel methods, in partic...
Abstract. By applying an idea of Borodin and Olshanski (2007), we study various scaling limits of de...
The eigenvalues of the kernel matrix play an important role in a number of kernel methods, in parti...
International audienceWe study the properties of the eigenvalues of Gram matrices in a non-asymptoti...
We consider nxn matrices whose (i, j)th entry is f(X-i(T) X-j), where X-1,..., X-n are i.i.d. standa...
We study the spectra of p×p random matrices K with off-diagonal (i, j) entry equal to n−1/2k(XTi Xj/...
A new form of empirical spectral distribution of a Wigner matrix Wn with weights specified by the ei...
We consider n-by-n matrices whose (i, j)th entry is f(XTi Xj), where X1,..., Xn are i.i.d. standard ...
Scaling level-spacing distribution functions in the ``bulk of the spectrum'' in random matr...
This paper focuses on the spectral distribution of kernel matrices related to radial basis functions...
This paper focuses on spectral distribution of kernel matrices related to radial basis functions. By...
The spectral behavior of kernel matrices built from complex multi-variate data is established in the...
This paper focuses on the spectral distribution of kernel matrices related to radial basis functions...
We study the properties of the eigenvalues of Gram matrices in a non-asymptotic setting. Using local...
Abstract. We study the properties of the eigenvalues of Gram matrices in a non-asymptotic setting. U...
The eigenvalues of the kernel matrix play an important role in a number of kernel methods, in partic...
Abstract. By applying an idea of Borodin and Olshanski (2007), we study various scaling limits of de...
The eigenvalues of the kernel matrix play an important role in a number of kernel methods, in parti...
International audienceWe study the properties of the eigenvalues of Gram matrices in a non-asymptoti...
We consider nxn matrices whose (i, j)th entry is f(X-i(T) X-j), where X-1,..., X-n are i.i.d. standa...
We study the spectra of p×p random matrices K with off-diagonal (i, j) entry equal to n−1/2k(XTi Xj/...
A new form of empirical spectral distribution of a Wigner matrix Wn with weights specified by the ei...
We consider n-by-n matrices whose (i, j)th entry is f(XTi Xj), where X1,..., Xn are i.i.d. standard ...
Scaling level-spacing distribution functions in the ``bulk of the spectrum'' in random matr...