Related papers: Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials

Related papers

Parametric correlations in non-Hermitian quantum chaos: random matrix approach [28.023703674946223]
We discuss the problem of characterizing the parametric correlations of spectral densities.<n>We derive an explicit, closed-form expression for the parametric number covariance in the systems of symmetry class $mathbfA$ for eigenvalues.<n>We also discuss a relation between parametric correlations of spectral densities and the distribution of the so-called eigenvector non-orthogonality factor.
arXiv Detail & Related papers (2026-06-18T18:09:35Z)
Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data [41.325451060228126]
We consider the conjugate kernel (CK), which is the nonlinear feature map of a feedforward NN, under a canonical nonlinearly separable dataset.<n>We develop a robust quadratic equivalent to the spiked CK matrix that enables a precise analysis of emergent informative spikes.<n>We derive a precise BBP-type phase transition in which linear classification via the CK eigenvectors becomes possible.
arXiv Detail & Related papers (2026-05-28T09:32:19Z)
Testing for latent structure via the Wilcoxon--Wigner random matrix of normalized rank statistics [0.20052993723676893]
We introduce and systematically study certain symmetric matrices, called Wilcoxon--Wigner random matrices.<n>We establish that the leading eigenvalue and corresponding eigenvector of Wilcoxon--Wigner random matrices admit fluctuations with explicit scaling terms.<n>Results enable rigorous parameter-free and distribution-free spectral methodology for addressing two hypothesis testing problems.
arXiv Detail & Related papers (2025-12-21T23:49:22Z)
Perturbative nonlinear J-matrix method of scattering in two dimensions [0.0]
We obtain the scattering matrix for the time-independent nonlinear Schrdinger equation in two dimensions with circular symmetry.<n>We present the theory for a general 2n 1 nonlinearity, where n is a natural number.<n>At certain value(s) of the energy, we observe the occurrence of bifurcation with two stable solutions.
arXiv Detail & Related papers (2025-11-18T14:15:26Z)
Explicit Discovery of Nonlinear Symmetries from Dynamic Data [50.20526548924647]
LieNLSD is the first method capable of determining the number of infinitesimal generators with nonlinear terms and their explicit expressions.<n>LieNLSD shows qualitative advantages over existing methods and improves the long rollout accuracy of neural PDE solvers by over 20%.
arXiv Detail & Related papers (2025-10-02T09:54:08Z)
Spectral distribution of sparse Gaussian Ensembles of Real Asymmetric Matrices [0.0]
We analyze the spectral statistics of the multiparametric Gaussian ensembles of real asymmetric matrices.<n>Our formulation provides a common mathematical formulation of the spectral statistics for a wide range of sparse real-asymmetric ensembles.
arXiv Detail & Related papers (2025-07-28T17:13:44Z)
Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models [76.52307406752556]
We derive a novel deterministic equivalence for the two-point function of a random resolvent.<n>We give a unified derivation of the performance of a wide variety of high-dimensional trained linear models with gradient descent.
arXiv Detail & Related papers (2025-02-07T16:45:40Z)
Entrywise application of non-linear functions on orthogonally invariant matrices [44.99833362998488]
We investigate how the entrywise application of a non-linear function to symmetric invariant random matrix ensembles alters the spectral distribution.<n>We find that in all those cases a Gaussian equivalence principle holds, that is, the effect of the non-linear function is the same as taking a linear combination of the involved matrices and an additional independent GOE.
arXiv Detail & Related papers (2024-12-09T19:41:09Z)
Deterministic equivalent of the Conjugate Kernel matrix associated to Artificial Neural Networks [0.0]
We show that the empirical spectral distribution of the Conjugate Kernel converges to a deterministic limit. More precisely we obtain a deterministic equivalent for its Stieltjes transform and its resolvent, with quantitative bounds involving both the dimension and the spectral parameter.
arXiv Detail & Related papers (2023-06-09T12:31:59Z)
Convolutional Filtering and Neural Networks with Non Commutative Algebras [153.20329791008095]
We study the generalization of non commutative convolutional neural networks. We show that non commutative convolutional architectures can be stable to deformations on the space of operators.
arXiv Detail & Related papers (2021-08-23T04:22:58Z)
Adversarially-Trained Nonnegative Matrix Factorization [77.34726150561087]
We consider an adversarially-trained version of the nonnegative matrix factorization. In our formulation, an attacker adds an arbitrary matrix of bounded norm to the given data matrix. We design efficient algorithms inspired by adversarial training to optimize for dictionary and coefficient matrices.
arXiv Detail & Related papers (2021-04-10T13:13:17Z)
Hessian Eigenspectra of More Realistic Nonlinear Models [73.31363313577941]
We make a emphprecise characterization of the Hessian eigenspectra for a broad family of nonlinear models. Our analysis takes a step forward to identify the origin of many striking features observed in more complex machine learning models.
arXiv Detail & Related papers (2021-03-02T06:59:52Z)
Nonlinear Independent Component Analysis for Continuous-Time Signals [85.59763606620938]
We study the classical problem of recovering a multidimensional source process from observations of mixtures of this process. We show that this recovery is possible for many popular models of processes (up to order and monotone scaling of their coordinates) if the mixture is given by a sufficiently differentiable, invertible function.
arXiv Detail & Related papers (2021-02-04T20:28:44Z)
Statistical properties of structured random matrices [0.0]
Spectral properties of Hermitian Toeplitz, Hankel, and Toeplitz-plus-Hankel random matrices with independent identically distributed entries are investigated. Our findings show that intermediate-type statistics is more ubiquitous and universal than was considered so far and open a new direction in random matrix theory.
arXiv Detail & Related papers (2020-12-21T18:00:14Z)
On Random Matrices Arising in Deep Neural Networks: General I.I.D. Case [0.0]
We study the distribution of singular values of product of random matrices pertinent to the analysis of deep neural networks. We use another, more streamlined, version of the techniques of random matrix theory to generalize the results of [22] to the case where the entries of the synaptic weight matrices are just independent identically distributed random variables with zero mean and finite fourth moment.
arXiv Detail & Related papers (2020-11-20T14:39:24Z)
Sparse Quantized Spectral Clustering [85.77233010209368]
We exploit tools from random matrix theory to make precise statements about how the eigenspectrum of a matrix changes under such nonlinear transformations. We show that very little change occurs in the informative eigenstructure even under drastic sparsification/quantization.
arXiv Detail & Related papers (2020-10-03T15:58:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.