Free dynamics of feature learning processes

DOI10.1007/S10955-022-03064-5MaRDI QIDQ2679634zbMATH OpenOpenAlexFDO

Authors Cyril Furtlehner

Publication date 23 January 2023

Published in Journal of Statistical Physics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2210.10702

zbMATH Keywords

dynamical systemsmachine learningneural networksrandom matrix theory

Mathematics Subject Classification ID

Probability theory on algebraic and topological structures (60Bxx) Linear inference, regression (62Jxx) Artificial intelligence (68Txx)

Cites work

• 10.1162/153244302760200704
• A random matrix approach to neural networks
• Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm
• Benign overfitting in linear regression
• Cleaning large correlation matrices: tools from random matrix theory
• Deep learning: a statistical viewpoint
• Deterministic equivalents for certain functionals of large random matrices
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup*
• Eigenvectors of some large sample covariance matrix ensembles
• Field Theories for Learning Probability Distributions
• Gaussian-spherical restricted Boltzmann machines
• Generalisation error in learning with random features and the hidden manifold model*
• High-dimensional asymptotics of prediction: ridge regression and classification
• High-dimensional dynamics of generalization error in neural networks
• scientific article; zbMATH DE number 1273988 (Why is no real title available?)
• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• Learning curves of generic features maps for realistic datasets with a teacher-student model*
• Limit laws for random matrices and free products
• Pattern recognition and machine learning.
• Random matrix methods for machine learning
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• Scaling description of generalization with number of parameters in deep learning
• Surprises in high-dimensional ridgeless least squares interpolation
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• The unreasonable effectiveness of deep learning in artificial intelligence
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Why does deep and cheap learning work so well?
• Wide neural networks of any depth evolve as linear models under gradient descent ^*

Cited in

(1)

• Free Dynamics of Feature Learning Processes

This page was built for publication: Free dynamics of feature learning processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2679634)