English
Related papers

Related papers: Asymptotic Singular Value Distribution of Linear C…

200 papers

Matrix completion algorithms recover a low rank matrix from a small fraction of the entries, each entry contaminated with additive errors. In practice, the singular vectors and singular values of the low rank matrix play a pivotal role for…

Methodology · Statistics 2016-05-03 Juhee Cho , Donggyu Kim , Karl Rohe

A fruitful approach for solving signal deconvolution problems consists of resorting to a frame-based convex variational formulation. In this context, parallel proximal algorithms and related alternating direction methods of multipliers have…

Other Computer Science · Computer Science 2015-05-28 Nelly Pustelnik , Jean-Christophe Pesquet , Caroline Chaux

Although deep convolutional neural networks (CNNs) have obtained outstanding performance in image superresolution (SR), their computational cost increases geometrically as CNN models get deeper and wider. Meanwhile, the features of…

Image and Video Processing · Electrical Eng. & Systems 2019-12-02 Seongmin Hwang , Gwanghuyn Yu , Cheolkon Jung , Jinyoung Kim

The classical random matrix theory is mostly focused on asymptotic spectral properties of random matrices as their dimensions grow to infinity. At the same time many recent applications from convex geometry to functional analysis to…

Functional Analysis · Mathematics 2014-03-05 Mark Rudelson , Roman Vershynin

We study the sample complexity of learning one-hidden-layer convolutional neural networks (CNNs) with non-overlapping filters. We propose a novel algorithm called approximate gradient descent for training CNNs, and show that, with high…

Machine Learning · Computer Science 2019-11-13 Yuan Cao , Quanquan Gu

The scattering transform is a wavelet-based model of Convolutional Neural Networks originally introduced by S. Mallat. Mallat's analysis shows that this network has desirable stability and invariance guarantees and therefore helps explain…

Signal Processing · Electrical Eng. & Systems 2021-10-12 Michael Perlmutter , Jieqian He , Mark Iwen , Matthew Hirn

A considerable amount of research in harmonic analysis has been devoted to non-linear estimators of signals contaminated by additive Gaussian noise. They are implemented by thresholding coefficients in a frame, which provide a sparse signal…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Nathanaël Cuvelle--Magar , Stéphane Mallat

Regularization in convolutional neural networks (CNNs) is usually addressed with dropout layers. However, dropout is sometimes detrimental in the convolutional part of a CNN as it simply sets to zero a percentage of pixels in the feature…

Image and Video Processing · Electrical Eng. & Systems 2021-08-29 Juan P. Vigueras-Guillén , Joan Lasenby , Frank Seeliger

We consider a product of an arbitrary number of independent rectangular Gaussian random matrices. We derive the mean densities of its eigenvalues and singular values in the thermodynamic limit, eventually verified numerically. These…

Statistical Mechanics · Physics 2011-06-28 Z. Burda , A. Jarosz , G. Livan , M. A. Nowak , A. Swiech

This paper is devoted to the asymptotic behavior of all eigenvalues of Symmetric (in general non Hermitian) Toeplitz matrices with moderately smooth symbols which trace out a simple loop on the complex plane line as the dimension of the…

Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks. Although performing convolution in Euclidean geometries is fairly straightforward, its extension to other…

Machine Learning · Computer Science 2019-01-04 Sameera Ramasinghe , Salman Khan , Nick Barnes

We present a neighborhood similarity layer (NSL) which induces appearance invariance in a network when used in conjunction with convolutional layers. We are motivated by the observation that, even though convolutional networks have low…

Computer Vision and Pattern Recognition · Computer Science 2017-07-05 Tolga Tasdizen , Mehdi Sajjadi , Mehran Javanmardi , Nisha Ramesh

We study two specific symmetric random block Toeplitz (of dimension $k \times k$) matrices: where the blocks (of size $n \times n$) are (i) matrices with i.i.d. entries, and (ii) asymmetric Toeplitz matrices. Under suitable assumptions on…

Probability · Mathematics 2011-11-09 Riddhipratim Basu , Arup Bose , Shirshendu Ganguly , Rajat Subhra Hazra

We establish universal Gaussian fluctuations for the mesoscopic linear eigenvalue statistics in the vicinity of the cusp-like singularities of the limiting spectral density for Wigner-type random matrices. Prior to this work, the linear…

Probability · Mathematics 2023-08-25 Volodymyr Riabov

Singular source terms expressed as weighted summations of Dirac-delta functions are regularized through approximation theory with convolution operators. We consider the numerical solution of scalar and one-dimensional hyperbolic…

Numerical Analysis · Mathematics 2016-11-18 Jean-Piero Suarez , Gustaaf Jacobs

We show the effectiveness of automatic differentiation in efficiently and correctly computing and controlling the spectrum of implicitly linear operators, a rich family of layer types including all standard convolutional and dense layers.…

Machine Learning · Computer Science 2024-10-08 Ali Ebrahimpour Boroojeny , Matus Telgarsky , Hari Sundaram

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Convolutional neural networks are very popular nowadays. Training neural networks is not an easy task. Each convolution corresponds to a structured transformation matrix. In order to help avoid the exploding/vanishing gradient problem, it…

Machine Learning · Computer Science 2021-02-09 Pei-Chang Guo

We study the spectrum of an asymmetric random matrix with block structured variances. The rows and columns of the random square matrix are divided into $D$ partitions with arbitrary size (linear in $N$). The parameters of the model are the…

Probability · Mathematics 2015-10-28 Johnatan Aljadeff , David Renfrew , Merav Stern

Deep neural networks have enormous representational power which leads them to overfit on most datasets. Thus, regularizing them is important in order to reduce overfitting and enhance their generalization capabilities. Recently, channel…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Sudhakar Kumawat , Gagan Kanojia , Shanmuganathan Raman