Precise high-dimensional asymptotics for quantifying heterogeneous transfers

MaRDI QIDQ6887454zbMATH OpenFDO

Authors Fan Yang, Hongyang R. Zhang, Sen Wu, Christopher Re, Weijie J. Su

Publication date 9 December 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/24-0454.html

zbMATH Keywords

covariate shifthigh-dimensional asymptoticsnegative transferrandom matrix theorytransfer learning

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A Dynamical Approach to Random Matrix Theory
• A modern maximum-likelihood theory for high-dimensional logistic regression
• A necessary and sufficient condition for edge universality at the largest singular values of covariance matrices
• A theory of learning from different domains
• Active clustering of biological sequences
• Adaptive and robust multi-task learning
• Bounds for linear multi-task learning
• CLT for eigenvalue statistics of large-dimensional general Fisher matrices with applications
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks
• High-dimensional statistics. A non-asymptotic viewpoint
• scientific article; zbMATH DE number 5957307 (Why is no real title available?)
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• Isotropic local laws for sample covariance and generalized Wigner matrices
• Learning from multiple sources
• Learning Theory and Kernel Machines
• Lectures on the Combinatorics of Free Probability
• Local law of addition of random matrices on optimal scale
• Mathematical Analysis of Machine Learning Algorithms
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over \ell_q-Balls
• Multi-view Regression Via Canonical Correlation Analysis
• Random Matrix Theory and Wireless Communications
• Spectral statistics of Erdős-Rényi graphs. I: Local semicircle law
• The common intuition to transfer learning can win or lose: case studies for linear regression
• Transfer Learning for High-Dimensional Linear Regression: Prediction, Estimation and Minimax Optimality
• Union support recovery in multi-task learning
• Universality of covariance matrices
• WONDER: weighted one-shot distributed ridge regression in high dimensions

Cited in

(1)

• Pseudo-labeling for kernel ridge regression under covariate shift

This page was built for publication: Precise high-dimensional asymptotics for quantifying heterogeneous transfers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6887454)