English
Related papers

Related papers: On Random Matrices Arising in Deep Neural Networks…

200 papers

We show that, under mild assumptions, the spectrum of a sum of independent random matrices is close to that of the Gaussian random matrix whose entries have the same mean and covariance. This nonasymptotic universality principle yields…

Probability · Mathematics 2024-06-26 Tatiana Brailovskaya , Ramon van Handel

Large random matrices appear in different fields of mathematics and physics such as combinatorics, probability theory, statistics, operator theory, number theory, quantum field theory, string theory etc... In the last ten years, they…

Probability · Mathematics 2007-05-23 Alice Guionnet

We briefly review the random matrix theory for large N by N matrices viewed as free random variables in a context of stochastic diffusion. We establish a surprising link between the spectral properties of matrix-valued multiplicative…

Statistical Mechanics · Physics 2007-05-23 Ewa Gudowska-Nowak , Romuald J. Janik , Jerzy Jurkiewicz , Maciej A. Nowak , Waldemar Wieczorek

We study the eigenvalue distribution of a random matrix, at a transition where a new connected component of the eigenvalue density support appears away from other connected components. Unlike previously studied critical points, which…

Mathematical Physics · Physics 2007-05-23 Bertrand Eynard

We compute analytically the probability distribution and moments of the sum and product of the non-zero eigenvalues and singular values of random matrices with (i) non-negative entries, (ii) fixed rank, and (iii) prescribed sums of the…

Statistical Mechanics · Physics 2025-06-17 Mark J. Crumpton , Yan V. Fyodorov , Pierpaolo Vivo

This thesis reviews recent progress on products of random matrices from the perspective of exactly solved Gaussian random matrix models. We derive exact formulae for the correlation functions for the eigen- and singular values at arbitrary…

Mathematical Physics · Physics 2015-10-22 J. R. Ipsen

Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has…

Machine Learning · Statistics 2020-09-18 Benjamin Bloem-Reddy , Yee Whye Teh

We investigate the universality of singular value and eigenvalue distributions of matrix valued functions of independent random matrices and apply these general results in several examples. In particular we determine the limit distribution…

Probability · Mathematics 2014-08-19 F. Götze , H. Kösters , A. Tikhomirov

Motivated by the asymptotic collective behavior of random and deterministic matrices, we propose an approximation (called "free deterministic equivalent") to quite general random matrix models, by replacing the matrices with operators…

Information Theory · Computer Science 2011-10-07 Roland Speicher , Carlos Vargas , Tobias Mai

Let $\a$ be a real-valued random variable of mean zero and variance 1. Let $M_n(\a)$ denote the $n \times n$ random matrix whose entries are iid copies of $\a$ and $\sigma_n(M_n(\a))$ denote the least singular value of $M_n(\a)$.…

Probability · Mathematics 2009-03-04 Terence Tao , Van Vu

It is a classical result of Wigner that for an hermitian matrix with independent entries on and above the diagonal, the mean empirical eigenvalue distribution converges weakly to the semicircle law as matrix size tends to infinity. In this…

Probability · Mathematics 2007-07-17 Katrin Hofmann-Credner , Michael Stolz

We review methods to calculate eigenvalue distributions of products of large random matrices. We discuss a generalization of the law of free multiplication to non-Hermitian matrices and give a couple of examples illustrating how to use…

Mathematical Physics · Physics 2015-06-17 Zdzislaw Burda

We study the singularity probability of n*n random matrices with i.i.d. entries from highly biased discrete distributions. We obtain sharp non-asymptotic bounds for this probability and derive estimates on the least singular values. Our…

Probability · Mathematics 2025-12-12 Zeyan Song

Random matrix theory is a well-developed area of probability theory that has numerous connections with other areas of mathematics and its applications. Much of the literature in this area is concerned with matrices that possess many exact…

Probability · Mathematics 2018-06-22 Ramon van Handel

We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to address limitations of the standard Gaussian prior. It has been proved in [26] that, as the number…

Machine Learning · Statistics 2026-05-14 Nicola Apollonio , Giovanni Franzina , Giovanni Luca Torrisi

Random matrix theory (RMT) is based on two assumptions: (1) matrix-element independence, and (2) base invariance. Most of the proposed generalizations keep the first assumption and violate the second. Recently, several authors presented…

Statistical Mechanics · Physics 2009-07-14 A. Y. Abul-Magd

We use freeness assumptions of random matrix theory to analyze the dynamical behavior of inference algorithms for probabilistic models with dense coupling matrices in the limit of large systems. For a toy Ising model, we are able to recover…

Statistical Mechanics · Physics 2023-07-19 Manfred Opper , Burak Çakmak

We establish, under a moment matching hypothesis, the local universality of the correlation functions associated with products of $M$ independent iid random matrices, as $M$ is fixed, and the sizes of the matrices tend to infinity. This…

Probability · Mathematics 2019-04-25 Phil Kopel , Sean O'Rourke , Van Vu

Despite the tremendous advancements in the field of network theory, very few studies have taken weights in the interactions into consideration that emerge naturally in all real world systems. Using random matrix analysis of a weighted…

Physics and Society · Physics 2016-02-25 Camellia Sarkar , Sarika Jalan

This study evaluates thresholds for removing singular values from singular value decomposition-based low-rank approximations of deep neural network weight matrices. Each weight matrix is modeled as the sum of signal and noise matrices. The…

Machine Learning · Statistics 2026-04-10 Kohei Nishikawa , Koki Shimizu , Hiroki Hashiguchi