Enhancing accuracy in deep learning using random matrix theory

DOI10.4208/JML.231220MaRDI QIDQ6955705zbMATH OpenFDO

Authors Leonid Berlyand, Étienne Sandier, Yitzchak Shmalo, Lei Zhang

Publication date 22 July 2025

Published in Journal of Machine Learning (Search for Journal in Brave)

zbMATH Keywords

deep learningpruningrandom matrix theoryMarchenko-Pastur distributionincreasing accuracy

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Random matrices (probabilistic aspects) (60B20)

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• scientific article; zbMATH DE number 7415108 (Why is no real title available?)
• scientific article; zbMATH DE number 3244317 (Why is no real title available?)
• Asymmetry helps: eigenvalue and eigenvector analyses of asymmetrically perturbed low-rank matrices
• Bootstrap confidence sets for spectral projectors of sample covariance
• Deep learning
• Eigenvector distribution in the critical regime of BBP transition
• Enhancing accuracy in deep learning using random matrix theory
• Entrywise Estimation of Singular Vectors of Low-Rank Matrices With Heteroskedasticity and Dependence
• Estimation of the Number of Spiked Eigenvalues in a Covariance Matrix by Bulk Eigenvalue Matching Analysis
• Flat Minima
• High-dimensional probability. An introduction with applications in data science
• Large-dimensional random matrix theory and its applications in deep learning and wireless communications
• Matrix denoising for weighted loss functions and heterogeneous signals
• Multivariate statistical analysis. A high-dimensional approach
• On Random Matrices Arising in Deep Neural Networks. Gaussian Case
• On random matrices arising in deep neural networks: General I.I.D. case
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Random matrix methods for machine learning
• Random matrix methods for wireless communications.
• Random perturbation of low rank matrices: improving classical bounds
• SVD-based DNN pruning and retraining
• Singular vector and singular subspace distribution for the matrix denoising model
• Stability for the training of deep neural networks and other classifiers
• The Eigenvectors of Single-Spiked Complex Wishart Matrices: Finite and Asymptotic Analyses
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• The singular values and vectors of low rank perturbations of large rectangular random matrices

Cited in

(1)

• Enhancing accuracy in deep learning using random matrix theory

This page was built for publication: Enhancing accuracy in deep learning using random matrix theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6955705)