The common intuition to transfer learning can win or lose: case studies for linear regression

DOI10.1137/23M1563062MaRDI QIDQ6583519zbMATH OpenFDO

Authors Yehuda Dar, Daniel LeJeune, Richard G. Baraniuk

Publication date 6 August 2024

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

Full work available at URL https://doi.org/10.1137/23M1563062

zbMATH Keywords

double descentlinear regressionoverparameterized learningridge regressiontransfer learning

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Ridge regression; shrinkage estimators (Lasso) (62J07) Computational learning theory (68Q32)

Cites work

• A jamming transition from under- to over-parametrization affects generalization in deep learning
• A model of double descent for high-dimensional binary linear classification
• Benign overfitting in linear regression
• Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks
• High-dimensional asymptotics of prediction: ridge regression and classification
• scientific article; zbMATH DE number 7626737 (Why is no real title available?)
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• Scaling description of generalization with number of parameters in deep learning
• Surprises in high-dimensional ridgeless least squares interpolation
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• Two models of double descent for weak features

Cited in

(1)

• Precise high-dimensional asymptotics for quantifying heterogeneous transfers

This page was built for publication: The common intuition to transfer learning can win or lose: case studies for linear regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6583519)