English
Related papers

Related papers: Relative concentration bounds for the spectrum of …

200 papers

We study concentration operators associated with either the discrete or the continuous Fourier transform, that is, operators that incorporate a spatial cut-off and a subsequent frequency cut-off to the Fourier inversion formula. Their…

Functional Analysis · Mathematics 2024-03-11 Felipe Marceca , José Luis Romero , Michael Speckbacher

We generalize finite-sample bounds for convex clustering to the setting where affinity weights appearing in the objective correspond to a general connected graph. These bounds and their analysis lead to a better understanding of clustering…

Machine Learning · Statistics 2026-05-26 Sam Rosen , Jason Xu

A method of resummation of infinite series of perturbation theory diagrams is applied for studying the properties of random band matrices. The topological classification of Feynman diagrams, which was actively used in last years for matrix…

Statistical Mechanics · Physics 2016-08-31 P. G. Silvestrov

Complex networks are characterized by heterogeneous distributions of the degree of nodes, which produce a large diversification of the roles of the nodes within the network. Several centrality measures have been introduced to rank nodes…

Physics and Society · Physics 2009-11-13 Nicola Perra , Santo Fortunato

Consider any random graph model where potential edges appear independently, with possibly different probabilities, and assume that the minimum expected degree is omega(ln n). We prove that the adjacency matrix and the Laplacian of that…

Combinatorics · Mathematics 2010-02-10 Roberto Imbuzeiro Oliveira

We study numerically the spectrum and eigenstate properties of the Google matrix of various examples of directed networks such as vocabulary networks of dictionaries and university World Wide Web networks. The spectra have gapless structure…

Information Retrieval · Computer Science 2010-05-27 B. Georgeot , O. Giraud , D. L. Shepelyansky

We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function $k(\cdot,\cdot)$. Our approach uses decoupling results for U-statistics and the non-commutative…

Machine Learning · Statistics 2025-11-07 Chiraag Kaushik , Justin Romberg , Vidya Muthukumar

Understanding the spectral properties of kernels offers a principled perspective on generalization and representation quality. While deep models achieve state-of-the-art accuracy in molecular property prediction, kernel methods remain…

Machine Learning · Computer Science 2025-10-17 Asma Jamali , Tin Sum Cheng , Rodrigo A. Vargas-Hernández

Statistical properties of non--symmetric real random matrices of size $M$, obtained as truncations of random orthogonal $N\times N$ matrices are investigated. We derive an exact formula for the density of eigenvalues which consists of two…

Statistical Mechanics · Physics 2010-10-21 Boris A. Khoruzhenko , Hans-Juergen Sommers , Karol Zyczkowski

This paper focuses on large neural networks whose synaptic connectivity matrices are randomly chosen from certain random matrix ensembles. The dynamics of these networks can be characterized by the eigenvalue spectra of their connectivity…

Disordered Systems and Neural Networks · Physics 2015-06-05 Yi Wei

How many samples are sufficient to guarantee that the eigenvectors and eigenvalues of the sample covariance matrix are close to those of the actual covariance matrix? For a wide family of distributions, including distributions with finite…

Machine Learning · Statistics 2017-02-20 Andreas Loukas

This paper studies the concentration properties of random codes. Specifically, we show that, for discrete memoryless channels, the error exponent of a randomly generated code with pairwise-independent codewords converges in probability to…

Information Theory · Computer Science 2022-03-16 Lan V. Truong , Giuseppe Cocco , Josep Font-Segura , Albert Guillén i Fàbregas

We study largest singular values of large random matrices, each with mean of a fixed rank $K$. Our main result is a limit theorem as the number of rows and columns approach infinity, while their ratio approaches a positive constant. It…

Probability · Mathematics 2021-03-02 Wlodek Bryc , Jack W. Silverstein

We derive concentration inequalities for the supremum norm of the difference between a kernel density estimator (KDE) and its point-wise expectation that hold uniformly over the selection of the bandwidth and under weaker conditions on the…

Statistics Theory · Mathematics 2020-01-01 Jisu Kim , Jaehyeok Shin , Alessandro Rinaldo , Larry Wasserman

Various methods in statistical learning build on kernels considered in reproducing kernel Hilbert spaces. In applications, the kernel is often selected based on characteristics of the problem and the data. This kernel is then employed to…

Machine Learning · Statistics 2024-03-12 Paul Dommel , Alois Pichler

We derive the exact form of the eigenvalue spectra of correlation matrices derived from a set of time-shifted, finite Brownian random walks (time-series). These matrices can be seen as random, real, asymmetric matrices with a special…

Physics and Society · Physics 2008-12-02 Christoly Biely , Stefan Thurner

Low-rank approximation of kernels is a fundamental mathematical problem with widespread algorithmic applications. Often the kernel is restricted to an algebraic variety, e.g., in problems involving sparse or low-rank data. We show that…

Machine Learning · Computer Science 2023-10-02 Jason M. Altschuler , Pablo A. Parrilo

The investigation of universality questions for local eigenvalue statistics continues to be a driving force in the theory of Random Matrices. For Matrix Models [53] the method of orthogonal polynomials can be used and the asymptotics of the…

Probability · Mathematics 2016-02-25 Thomas Kriecherbauer , Kristina Schubert , Katharina Schüler , Martin Venker

We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels. We prove that, with normalized multi-channel input and ReLU activation, the…

Machine Learning · Computer Science 2022-03-18 Amnon Geifman , Meirav Galun , David Jacobs , Ronen Basri

We use the steepest descents method to study the integral kernel of a family of normal random matrix ensembles with eigenvalue distribution P_{N}(z_{1},...,z_{N}) = Z_{N}^{-1} e^{-N\Sigma_{i=1}^{N}V_{\alpha}(z_{i})}…

Mathematical Physics · Physics 2015-05-28 Alexei M. Veneziani , Tiago Pereira , Domingos H. U. Marchetti
‹ Prev 1 4 5 6 7 8 10 Next ›