When do neural networks outperform kernel methods?*

DOI10.1088/1742-5468/AC3A81OpenAlexW4206434796MaRDI QIDQ5020050

No author found.

Publication date: 3 January 2022

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.13409

zbMATH Keywords

learning theorymachine learningdeep learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (10)

Deep learning: a statistical viewpoint ⋮ Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation ⋮ Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration ⋮ Learning curves of generic features maps for realistic datasets with a teacher-student model* ⋮ Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime* ⋮ Particle dual averaging: optimization of mean field neural network with global convergence rate analysis* ⋮ Relative stability toward diffeomorphisms indicates performance in deep nets* ⋮ Algorithmic Regularization in Model-Free Overparametrized Asymmetric Matrix Factorization ⋮ Learning sparse features can lead to overfitting in neural networks ⋮ The interpolation phase transition in neural networks: memorization and generalization under lazy training

Uses Software

• TensorFlow
• Adam
• neural-tangents

Cites Work

• The landscape of empirical risk for nonconvex losses
• Adapting to Unknown Smoothness via Wavelet Shrinkage
• A mean field view of the landscape of two-layer neural networks
• Breaking the Curse of Dimensionality with Convex Neural Networks

This page was built for publication: When do neural networks outperform kernel methods?*