Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm

DOI10.1088/1742-5468/abc61dOpenAlexW3117575511MaRDI QIDQ5857446

Matthieu Wyart, Mario Geiger, Stefano Spigler

Publication date: 1 April 2021

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

Full work available at URL: https://arxiv.org/abs/1905.10843

zbMATH Keywords

machine learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (5)

Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime* ⋮ Locality defeats the curse of dimensionality in convolutional teacher–student scenarios* ⋮ Free dynamics of feature learning processes ⋮ Landscape and training regimes in deep learning ⋮ Unnamed Item

Uses Software

• IntDim

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Measuring the strangeness of strange attractors
• Interpolation of spatial data. Some theory for kriging
• Predicting random fields with increasing dense observations
• Novel high intrinsic dimensionality estimators
• Optimal rates for the regularized least-squares algorithm
• Statistical Mechanics of Learning
• Optimal errors and phase transitions in high-dimensional generalized linear models
• Breaking the Curse of Dimensionality with Convex Neural Networks

This page was built for publication: Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm