Random features and polynomial rules

DOI10.21468/SCIPOSTPHYS.18.1.039MaRDI QIDQ7029104zbMATH OpenFDO

Authors Fabián Aguirre López, Silvio Franz, Mauro Pastore

Publication date 11 February 2025

Published in SciPost Physics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.21468/SCIPOSTPHYS.18.1.039

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Disordered systems (random Ising models, random Schrödinger operators, etc.) in equilibrium statistical mechanics (82B44)

Cites work

• A first course in random matrix theory: for physicists, engineers and data scientists
• Bayesian learning for neural networks
• Central limit theorems for non-linear functionals of Gaussian fields
• Critical properties of the SAT/UNSAT transitions in the classification problem of structured data
• Deep learning: a statistical viewpoint
• Generalisation error in learning with random features and the hidden manifold model*
• Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration
• Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*
• Generalization from correlated sets of patterns in the perceptron
• scientific article; zbMATH DE number 3096864 (Why is no real title available?)
• Introduction to random matrices. Theory and practice
• Kernels as features: on kernels, margins, and low-dimensional mappings
• Learning curves for deep structured Gaussian feature models
• Learning of higher-order perceptrons with tunable complexities
• Linearized two-layers neural networks in high dimension
• Marchenko–Pastur law with relaxed independence conditions
• Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
• Moment bounds and central limit theorems for Gaussian subordinated arrays
• Precise learning curves and higher-order scaling limits for dot-product kernel regression
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• Replica analysis of overfitting in generalized linear regression models
• Scikit-learn: machine learning in Python
• Statistical mechanics of learning
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• The interpolation phase transition in neural networks: memorization and generalization under lazy training
• The space of interactions in neural network models
• The spectrum of kernel random matrices
• Universality Laws for High-Dimensional Learning With Random Features
• When do neural networks outperform kernel methods?*

Cited in

(1)

• Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers

This page was built for publication: Random features and polynomial rules

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7029104)