scientific article; zbMATH DE number 7415108
From MaRDI portal
Publication:5159443
Recommendations
- Nonlinear random matrix theory for deep learning
- On Random Matrices Arising in Deep Neural Networks. Gaussian Case
- Universal characteristics of deep neural network loss surfaces from random matrix theory
- On random matrices arising in deep neural networks: General I.I.D. case
- On the Learnability of Random Deep Networks
- Deep regularization and direct training of the inner layers of neural networks with kernel flows
- Products of many large random matrices and gradients in deep neural networks
Cites work
- A mean field view of the landscape of two-layer neural networks
- Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
- Beyond universality in random matrix theory
- Central limit theorem for eigenvectors of heavy tailed matrices
- Cleaning large correlation matrices: tools from random matrix theory
- Critical phenomena in natural sciences. Chaos, fractals, selforganization and disorder: Concepts and tools.
- Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
- Empirical distributions of stock returns: between the stretched exponential and the power law?
- Extreme eigenvalues of sparse, heavy tailed random matrices
- Extreme value problems in random matrix theory and other disordered systems
- Financial applications of random matrix theory: a short review
- Generalized extreme value statistics and sum of correlated variables
- Heavy-Tail Phenomena
- Learning and generalization with the information bottleneck
- Limit theory for the largest eigenvalues of sample covariance matrices with heavy-tails
- On consistency and sparsity for principal components analysis in high dimensions
- On the distribution of the largest eigenvalue in principal components analysis
- On the top eigenvalue of heavy-tailed random matrices
- Pattern classification.
- Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
- Poisson convergence for the largest eigenvalues of heavy tailed random matrices
- Power-law distributions in binned empirical data
- Power-law distributions in empirical data
- Random matrix theory
- Random Matrix Theory and Wireless Communications
- Random matrix theory in statistics: a review
- Recent results about the largest eigenvalue of random covariance matrices and statistical application
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- Rigorous learning curve bounds from statistical mechanics
- Statistical mechanics of learning
- Statistical Physics of Spin Glasses and Information Processing
- The Distributions of Random Matrix Theory and their Applications
- The largest eigenvalue of rank one deformation of large Wigner matrices
- The spectrum edge of random matrix ensembles.
- The spectrum of heavy tailed random matrices
- Universality classes for extreme-value statistics
- Why does unsupervised pre-training help deep learning?
Cited in
(13)- Halting time is predictable for large models: a universality property and average-case analysis
- Stop Memorizing: A Data-Dependent Regularization Framework for Intrinsic Pattern Learning
- Accessibility measure for eternal inflation: dynamical criticality and Higgs metastability
- Search optimization, funnel topography, and dynamical criticality on the string landscape
- Understanding Implicit Regularization in Over-Parameterized Single Index Model
- Optimization in machine learning: a distribution-space approach
- Global law of conjugate kernel random matrices with heavy-tailed weights
- Enhancing accuracy in deep learning using random matrix theory
- Per-example gradient regularization improves learning signals from noisy data
- A rainbow in deep network black boxes
- Random weights of DNNs and emergence of fixed points
- Autoregressive random matrix theory based on the q-dependent detrended cross-correlation coefficient
- Deep neural network compression via data-driven low-rank singular value decomposition
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5159443)
