Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks

DOI10.1137/22M1469559OpenAlexW3035203578MaRDI QIDQ5885828

Yehuda Dar, Richard G. Baraniuk

Publication date: 30 March 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.07002

zbMATH Keywords

linear regressiontransfer learningdouble descentoverparameterized learning

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Computational learning theory (68Q32)

Uses Software

• PDCO

Cites Work

• Surprises in high-dimensional ridgeless least squares interpolation
• Atomic Decomposition by Basis Pursuit
• How Many Variables Should be Entered in a Regression Equation?
• Two Models of Double Descent for Weak Features
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• Benign overfitting in linear regression
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• 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: Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks