A random matrix approach to neural networks
From MaRDI portal
Publication:1650102
DOI10.1214/17-AAP1328zbMath1391.60010arXiv1702.05419OpenAlexW2963650649WikidataQ130038206 ScholiaQ130038206MaRDI QIDQ1650102
Zhenyu Liao, Cosme Louart, Romain Couillet
Publication date: 29 June 2018
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1702.05419
Random matrices (probabilistic aspects) (60B20) Neural networks for/in biological studies, artificial life and related topics (92B20) Random matrices (algebraic aspects) (15B52) Neural nets and related approaches to inference from stochastic processes (62M45)
Related Items
Deep learning: a statistical viewpoint ⋮ On the empirical spectral distribution for certain models related to sample covariance matrices with different correlations ⋮ Large-dimensional random matrix theory and its applications in deep learning and wireless communications ⋮ Free dynamics of feature learning processes ⋮ Designing universal causal deep learning models: The geometric (Hyper)transformer ⋮ Halting time is predictable for large models: a universality property and average-case analysis ⋮ Eigenvalue distribution of some nonlinear models of random matrices ⋮ A note on the Pennington-Worah distribution ⋮ Unnamed Item ⋮ A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent* ⋮ Generalisation error in learning with random features and the hidden manifold model*
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Kernel spectral clustering of large dimensional data
- Almost sure localization of the eigenvalues in a Gaussian information plus noise model. Application to the spiked models.
- The singular values and vectors of low rank perturbations of large rectangular random matrices
- Hanson-Wright inequality and sub-Gaussian concentration
- The spectrum of kernel random matrices
- Spectral analysis of large dimensional random matrices
- Concentration of measure and spectra of random matrices: applications to correlation matrices, elliptical distributions and beyond
- No eigenvalues outside the support of the limiting spectral distribution of large-dimensional sample covariance matrices
- Multilayer feedforward networks are universal approximators
- On the empirical distribution of eigenvalues of a class of large dimensional random matrices
- Analysis of the limiting spectral distribution of large dimensional random matrices
- The random matrix regime of Maronna's M-estimator with elliptically distributed samples
- On the signal-to-interference ratio of CDMA systems in wireless communications
- Random Beamforming Over Quasi-Static and Fading Channels: A Deterministic Equivalent Approach
- Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
- A Large Dimensional Analysis of Least Squares Support Vector Machines
- A Central Limit Theorem for the SINR at the LMMSE Estimator Output for Large-Dimensional Signals
- DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
- AN EXAMPLE IN THE THEORY OF THE SPECTRUM OF A FUNCTION
