Triple descent and the two kinds of overfitting: where and why do they appear?*

DOI10.1088/1742-5468/ac3909OpenAlexW4200030970MaRDI QIDQ5020037

Stéphane D'Ascoli, Levent Sagun, Giulio Biroli

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/2006.03509

zbMATH Keywords

machine learningdeep learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (1)

Dimensionality Reduction, Regularization, and Generalization in Overparameterized Regressions

Uses Software

• ImageNet
• AlexNet

Cites Work

• A note on the Pennington-Worah distribution
• Statistical Mechanics of Learning
• The simplest model of jamming
• Statistical mechanics of complex neural systems and high dimensional data
• Generalization in a linear perceptron in the presence of noise
• Scaling description of generalization with number of parameters in deep learning
• A jamming transition from under- to over-parametrization affects generalization in deep learning

This page was built for publication: Triple descent and the two kinds of overfitting: where and why do they appear?*